Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.8460. Min Act: -0.1700
Data Index: 2560451 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.5648. Min Act: -0.1700
Data Index: 1894623 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.2523. Min Act: -0.1700
Data Index: 5307518 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.2523. Min Act: -0.1700
Data Index: 8218989 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.2835. Min Act: -0.1700
Data Index: 6229107 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.2523. Min Act: -0.1700
Data Index: 4210214 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.1898. Min Act: -0.1700
Data Index: 1775187 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.2210. Min Act: -0.1700
Data Index: 8375452 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.1273. Min Act: -0.1700
Data Index: 4502352 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.0960. Min Act: -0.1700
Data Index: 2140355 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.0648. Min Act: -0.1700
Data Index: 4801225 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8460. Min Range: -6.8460
Max Act: 6.0023. Min Act: -0.1700
Data Index: 1155637 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8460. Min Range: -6.8460
Max Act: 5.9710. Min Act: -0.1700
Data Index: 8398097 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8460. Min Range: -6.8460
Max Act: 5.9398. Min Act: -0.1700
Data Index: 2595787 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8460. Min Range: -6.8460
Max Act: 5.9085. Min Act: -0.1700
Data Index: 4859351 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8460. Min Range: -6.8460
Max Act: 5.9398. Min Act: -0.1700
Data Index: 4133173 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8460. Min Range: -6.8460
Max Act: 5.8773. Min Act: -0.1700
Data Index: 6590579 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8460. Min Range: -6.8460
Max Act: 5.9085. Min Act: -0.1700
Data Index: 8355508 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8460. Min Range: -6.8460
Max Act: 5.9085. Min Act: -0.1700
Data Index: 3861992 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8460. Min Range: -6.8460
Max Act: 5.9085. Min Act: -0.1700
Data Index: 6809418 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19