Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 761 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.8560. Min Act: -0.1700
Data Index: 418218 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.8872. Min Act: -0.1700
Data Index: 4036367 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.8560. Min Act: -0.1700
Data Index: 4450673 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.8247. Min Act: -0.1700
Data Index: 4020680 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.7622. Min Act: -0.1700
Data Index: 2045034 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.7622. Min Act: -0.1700
Data Index: 1001415 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.7622. Min Act: -0.1700
Data Index: 2385934 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.6997. Min Act: -0.1700
Data Index: 5619113 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.6060. Min Act: -0.1700
Data Index: 4026592 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5747. Min Act: -0.1700
Data Index: 7889942 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5747. Min Act: -0.1700
Data Index: 4851244 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.6060. Min Act: -0.1700
Data Index: 6456648 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.6372. Min Act: -0.1700
Data Index: 8509908 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5435. Min Act: -0.1700
Data Index: 4815313 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5435. Min Act: -0.1700
Data Index: 3950846 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5122. Min Act: -0.1700
Data Index: 2630288 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5122. Min Act: -0.1700
Data Index: 6752044 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5122. Min Act: -0.1700
Data Index: 6608863 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5122. Min Act: -0.1700
Data Index: 5415013 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8872. Min Range: -5.8872
Max Act: 5.5122. Min Act: -0.1700
Data Index: 8509907 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19