Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3888 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.3523. Min Act: -0.1700
Data Index: 2091964 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.3211. Min Act: -0.1700
Data Index: 2091963 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2898. Min Act: -0.1700
Data Index: 103061 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2273. Min Act: -0.1700
Data Index: 6082468 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1648. Min Act: -0.1700
Data Index: 7061369 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1961. Min Act: -0.1700
Data Index: 3894622 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2273. Min Act: -0.1700
Data Index: 1153055 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1961. Min Act: -0.1700
Data Index: 8257840 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1961. Min Act: -0.1700
Data Index: 565619 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1336. Min Act: -0.1700
Data Index: 4975504 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1023. Min Act: -0.1700
Data Index: 704080 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1023. Min Act: -0.1700
Data Index: 8759559 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1023. Min Act: -0.1700
Data Index: 7301076 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1023. Min Act: -0.1700
Data Index: 2361138 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.0711. Min Act: -0.1700
Data Index: 5445094 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.0398. Min Act: -0.1700
Data Index: 1224975 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.0085. Min Act: -0.1700
Data Index: 4185123 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.0398. Min Act: -0.1700
Data Index: 8108446 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.0398. Min Act: -0.1700
Data Index: 590551 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.9773. Min Act: -0.1700
Data Index: 4572949 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19