Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2679 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.7279. Min Act: -0.1700
Data Index: 3862839 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.6654. Min Act: -0.1700
Data Index: 6206675 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.7279. Min Act: -0.1700
Data Index: 8684455 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.6654. Min Act: -0.1700
Data Index: 2199971 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.5404. Min Act: -0.1700
Data Index: 1200069 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.4779. Min Act: -0.1700
Data Index: 4487571 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.4779. Min Act: -0.1700
Data Index: 4910164 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.4779. Min Act: -0.1700
Data Index: 5129177 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.4154. Min Act: -0.1700
Data Index: 1397499 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.4154. Min Act: -0.1700
Data Index: 3376828 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2904. Min Act: -0.1700
Data Index: 7260838 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2279. Min Act: -0.1700
Data Index: 5253951 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2279. Min Act: -0.1700
Data Index: 5253952 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2904. Min Act: -0.1700
Data Index: 459996 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2904. Min Act: -0.1700
Data Index: 5862619 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2279. Min Act: -0.1700
Data Index: 6098439 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2279. Min Act: -0.1700
Data Index: 1926565 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2279. Min Act: -0.1700
Data Index: 1286390 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.2279. Min Act: -0.1700
Data Index: 1008356 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7279. Min Range: -11.7279
Max Act: 11.1654. Min Act: -0.1700
Data Index: 5013361 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19