Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2693 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.3094. Min Act: -0.1700
Data Index: 96197 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.2156. Min Act: -0.1700
Data Index: 5049229 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.2156. Min Act: -0.1700
Data Index: 3030791 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.1531. Min Act: -0.1700
Data Index: 7521171 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.0906. Min Act: -0.1700
Data Index: 3216471 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.1219. Min Act: -0.1700
Data Index: 3456260 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.1219. Min Act: -0.1700
Data Index: 6051556 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.1219. Min Act: -0.1700
Data Index: 8556695 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.0594. Min Act: -0.1700
Data Index: 2070288 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3094. Min Range: -4.3094
Max Act: 4.0906. Min Act: -0.1700
Data Index: 1996360 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9968. Min Act: -0.1700
Data Index: 820724 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9968. Min Act: -0.1700
Data Index: 3158726 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9968. Min Act: -0.1700
Data Index: 7420054 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9968. Min Act: -0.1700
Data Index: 2276493 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9968. Min Act: -0.1700
Data Index: 2774504 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9656. Min Act: -0.1700
Data Index: 5679079 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9656. Min Act: -0.1700
Data Index: 5066923 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9499. Min Act: -0.1700
Data Index: 5195706 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9499. Min Act: -0.1700
Data Index: 5663021 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3094. Min Range: -4.3094
Max Act: 3.9343. Min Act: -0.1700
Data Index: 1914164 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19