Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 565 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.5273. Min Range: -9.5273
Max Act: 9.5273. Min Act: -0.1700
Data Index: 6018340 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5273. Min Range: -9.5273
Max Act: 9.5273. Min Act: -0.1700
Data Index: 7971443 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5273. Min Range: -9.5273
Max Act: 9.3398. Min Act: -0.1700
Data Index: 5876943 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5273. Min Range: -9.5273
Max Act: 9.2773. Min Act: -0.1700
Data Index: 6711778 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5273. Min Range: -9.5273
Max Act: 9.1523. Min Act: -0.1700
Data Index: 2110781 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5273. Min Range: -9.5273
Max Act: 9.1523. Min Act: -0.1700
Data Index: 8490550 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5273. Min Range: -9.5273
Max Act: 9.0898. Min Act: -0.1700
Data Index: 2987126 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9648. Min Act: -0.1700
Data Index: 3717090 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9648. Min Act: -0.1700
Data Index: 5721979 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9648. Min Act: -0.1700
Data Index: 4693225 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9648. Min Act: -0.1700
Data Index: 2649443 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9648. Min Act: -0.1700
Data Index: 6881922 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9648. Min Act: -0.1700
Data Index: 5834523 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9023. Min Act: -0.1700
Data Index: 8154130 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9023. Min Act: -0.1700
Data Index: 6284813 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.9023. Min Act: -0.1700
Data Index: 402432 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.8398. Min Act: -0.1700
Data Index: 3900658 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.8398. Min Act: -0.1700
Data Index: 1249213 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.8398. Min Act: -0.1700
Data Index: 6609629 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5273. Min Range: -9.5273
Max Act: 8.8398. Min Act: -0.1700
Data Index: 1114066 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19