Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.8406. Min Act: -0.1700
Data Index: 1936824 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.7156. Min Act: -0.1700
Data Index: 4198023 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.7156. Min Act: -0.1700
Data Index: 6406765 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.7156. Min Act: -0.1700
Data Index: 8480536 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.6844. Min Act: -0.1700
Data Index: 1145215 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.6844. Min Act: -0.1700
Data Index: 7849894 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.6219. Min Act: -0.1700
Data Index: 75703 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5906. Min Act: -0.1700
Data Index: 4198028 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5594. Min Act: -0.1700
Data Index: 816535 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 7182597 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 1557447 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 2238911 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 7765759 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 1292681 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 5502483 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 2657136 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4656. Min Act: -0.1700
Data Index: 2445404 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4656. Min Act: -0.1700
Data Index: 3175591 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4656. Min Act: -0.1700
Data Index: 7527267 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4031. Min Act: -0.1700
Data Index: 6976268 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19