Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.8643. Min Act: -0.1700
Data Index: 6626527 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.8018. Min Act: -0.1700
Data Index: 4403894 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.7080. Min Act: -0.1700
Data Index: 1736443 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.7705. Min Act: -0.1700
Data Index: 6702169 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.7393. Min Act: -0.1700
Data Index: 5642903 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.6455. Min Act: -0.1700
Data Index: 7293683 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.6455. Min Act: -0.1700
Data Index: 6441896 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.5830. Min Act: -0.1700
Data Index: 7941945 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.6143. Min Act: -0.1700
Data Index: 921638 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.6143. Min Act: -0.1700
Data Index: 3515131 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.5518. Min Act: -0.1700
Data Index: 7743246 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.5205. Min Act: -0.1700
Data Index: 8423610 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.5205. Min Act: -0.1700
Data Index: 4292407 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.5205. Min Act: -0.1700
Data Index: 3335373 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.4893. Min Act: -0.1700
Data Index: 2636548 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.4893. Min Act: -0.1700
Data Index: 4335099 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.4893. Min Act: -0.1700
Data Index: 6180441 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.4580. Min Act: -0.1700
Data Index: 2139008 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.4580. Min Act: -0.1700
Data Index: 2335124 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8643. Min Range: -6.8643
Max Act: 6.4893. Min Act: -0.1700
Data Index: 2152832 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19