Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 338 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1497. Min Range: -8.1497
Max Act: 8.1497. Min Act: -0.1700
Data Index: 6202471 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1497. Min Range: -8.1497
Max Act: 8.0872. Min Act: -0.1700
Data Index: 2561027 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.9310. Min Act: -0.1700
Data Index: 4587653 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.6497. Min Act: -0.1700
Data Index: 5983650 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.5560. Min Act: -0.1700
Data Index: 2495819 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.4935. Min Act: -0.1700
Data Index: 1043674 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.4622. Min Act: -0.1700
Data Index: 791750 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.4310. Min Act: -0.1700
Data Index: 3358998 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.4310. Min Act: -0.1700
Data Index: 5122259 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.3372. Min Act: -0.1700
Data Index: 4621448 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.3372. Min Act: -0.1700
Data Index: 6481458 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.2122. Min Act: -0.1700
Data Index: 8177392 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.2435. Min Act: -0.1700
Data Index: 8580748 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.2435. Min Act: -0.1700
Data Index: 6021892 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.1810. Min Act: -0.1700
Data Index: 6263341 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.2435. Min Act: -0.1700
Data Index: 2118721 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.2122. Min Act: -0.1700
Data Index: 5134885 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.2435. Min Act: -0.1700
Data Index: 8751359 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.1497. Min Act: -0.1700
Data Index: 3104305 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1497. Min Range: -8.1497
Max Act: 7.0560. Min Act: -0.1700
Data Index: 2522552 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19