Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4839 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.9393. Min Act: -0.1700
Data Index: 2109077 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.8456. Min Act: -0.1700
Data Index: 4452255 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.8143. Min Act: -0.1700
Data Index: 8616701 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.8456. Min Act: -0.1700
Data Index: 7034721 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.7206. Min Act: -0.1700
Data Index: 2706070 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.7206. Min Act: -0.1700
Data Index: 1224465 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.6893. Min Act: -0.1700
Data Index: 5683633 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.6581. Min Act: -0.1700
Data Index: 3795976 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.6268. Min Act: -0.1700
Data Index: 478799 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.6268. Min Act: -0.1700
Data Index: 8486730 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.6268. Min Act: -0.1700
Data Index: 2774980 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5956. Min Act: -0.1700
Data Index: 6422661 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5956. Min Act: -0.1700
Data Index: 2646025 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5643. Min Act: -0.1700
Data Index: 1602094 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5643. Min Act: -0.1700
Data Index: 4980859 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5643. Min Act: -0.1700
Data Index: 1661854 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5643. Min Act: -0.1700
Data Index: 1835325 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5018. Min Act: -0.1700
Data Index: 8097078 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5018. Min Act: -0.1700
Data Index: 4397721 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9393. Min Range: -5.9393
Max Act: 5.5018. Min Act: -0.1700
Data Index: 8285074 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19