Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 836 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.6350. Min Act: -0.1700
Data Index: 6285382 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.6038. Min Act: -0.1700
Data Index: 2255420 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.6038. Min Act: -0.1700
Data Index: 5386780 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.5725. Min Act: -0.1700
Data Index: 1500012 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.5725. Min Act: -0.1700
Data Index: 5296695 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.4788. Min Act: -0.1700
Data Index: 6194576 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.4475. Min Act: -0.1700
Data Index: 1624813 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.4475. Min Act: -0.1700
Data Index: 878477 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.4475. Min Act: -0.1700
Data Index: 4710659 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.4163. Min Act: -0.1700
Data Index: 5688351 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3850. Min Act: -0.1700
Data Index: 8070002 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3538. Min Act: -0.1700
Data Index: 4577796 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3538. Min Act: -0.1700
Data Index: 2534604 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3538. Min Act: -0.1700
Data Index: 3330061 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3538. Min Act: -0.1700
Data Index: 8191216 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3538. Min Act: -0.1700
Data Index: 6614384 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3225. Min Act: -0.1700
Data Index: 8674486 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3225. Min Act: -0.1700
Data Index: 1171878 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.3850. Min Act: -0.1700
Data Index: 3842979 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6350. Min Range: -6.6350
Max Act: 6.2600. Min Act: -0.1700
Data Index: 7119687 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19