Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 194 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6965. Min Range: -8.6965
Max Act: 8.6965. Min Act: -0.1700
Data Index: 4465258 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6965. Min Range: -8.6965
Max Act: 8.4465. Min Act: -0.1700
Data Index: 2177536 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6965. Min Range: -8.6965
Max Act: 8.4153. Min Act: -0.1700
Data Index: 8621273 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6965. Min Range: -8.6965
Max Act: 8.3215. Min Act: -0.1700
Data Index: 5629230 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6965. Min Range: -8.6965
Max Act: 8.3528. Min Act: -0.1700
Data Index: 3901768 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6965. Min Range: -8.6965
Max Act: 8.1340. Min Act: -0.1700
Data Index: 8536292 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6965. Min Range: -8.6965
Max Act: 8.0090. Min Act: -0.1700
Data Index: 5502993 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.7903. Min Act: -0.1700
Data Index: 6445660 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.6653. Min Act: -0.1700
Data Index: 998035 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.6340. Min Act: -0.1700
Data Index: 7672906 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.6653. Min Act: -0.1700
Data Index: 1771351 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.5090. Min Act: -0.1700
Data Index: 1965033 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.4778. Min Act: -0.1700
Data Index: 956351 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.5715. Min Act: -0.1700
Data Index: 900681 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.5090. Min Act: -0.1700
Data Index: 70488 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.4778. Min Act: -0.1700
Data Index: 1106242 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.5403. Min Act: -0.1700
Data Index: 5631224 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.5090. Min Act: -0.1700
Data Index: 3552327 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.5090. Min Act: -0.1700
Data Index: 8473570 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6965. Min Range: -8.6965
Max Act: 7.5090. Min Act: -0.1700
Data Index: 4997330 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19