Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1789 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0116. Min Range: -8.0116
Max Act: 8.0116. Min Act: -0.1700
Data Index: 8001515 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.9491. Min Act: -0.1700
Data Index: 2745290 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.9491. Min Act: -0.1700
Data Index: 7647622 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.9491. Min Act: -0.1700
Data Index: 2265928 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.9491. Min Act: -0.1700
Data Index: 8630262 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.8241. Min Act: -0.1700
Data Index: 8817305 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.8241. Min Act: -0.1700
Data Index: 889604 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.7616. Min Act: -0.1700
Data Index: 5027807 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6991. Min Act: -0.1700
Data Index: 6735682 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.7616. Min Act: -0.1700
Data Index: 3705580 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6991. Min Act: -0.1700
Data Index: 8176787 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6991. Min Act: -0.1700
Data Index: 2880496 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6366. Min Act: -0.1700
Data Index: 8202403 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6054. Min Act: -0.1700
Data Index: 8520503 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6366. Min Act: -0.1700
Data Index: 5964707 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6054. Min Act: -0.1700
Data Index: 446707 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.5741. Min Act: -0.1700
Data Index: 760009 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6054. Min Act: -0.1700
Data Index: 466273 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.5429. Min Act: -0.1700
Data Index: 2392900 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0116. Min Range: -8.0116
Max Act: 7.6054. Min Act: -0.1700
Data Index: 8151640 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19