Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 794 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.6281. Min Act: -0.1700
Data Index: 7756932 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.3781. Min Act: -0.1700
Data Index: 7766746 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.3469. Min Act: -0.1700
Data Index: 3245323 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.3469. Min Act: -0.1700
Data Index: 2485737 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.3156. Min Act: -0.1700
Data Index: 3363848 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.3156. Min Act: -0.1700
Data Index: 4417878 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.2219. Min Act: -0.1700
Data Index: 5744423 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.2219. Min Act: -0.1700
Data Index: 3890673 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.2219. Min Act: -0.1700
Data Index: 2465626 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.1906. Min Act: -0.1700
Data Index: 7813026 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.1594. Min Act: -0.1700
Data Index: 1689667 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.1594. Min Act: -0.1700
Data Index: 1697633 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.1594. Min Act: -0.1700
Data Index: 3834705 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.1594. Min Act: -0.1700
Data Index: 3443750 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.1906. Min Act: -0.1700
Data Index: 3890674 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.1594. Min Act: -0.1700
Data Index: 5199342 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.1281. Min Act: -0.1700
Data Index: 8186182 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.0656. Min Act: -0.1700
Data Index: 2680807 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.0656. Min Act: -0.1700
Data Index: 6857509 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6281. Min Range: -6.6281
Max Act: 6.0969. Min Act: -0.1700
Data Index: 5057534 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19