Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 795 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.7053. Min Act: -0.1700
Data Index: 1322353 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.5178. Min Act: -0.1590
Data Index: 7592035 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.3928. Min Act: -0.1661
Data Index: 4806055 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.4241. Min Act: -0.1700
Data Index: 5831747 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.3616. Min Act: -0.1614
Data Index: 7181574 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.2991. Min Act: -0.1700
Data Index: 1927117 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.2991. Min Act: -0.1700
Data Index: 4365153 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.3303. Min Act: -0.1700
Data Index: 6218597 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.1741. Min Act: -0.1700
Data Index: 4127219 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.2053. Min Act: -0.1700
Data Index: 1354247 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.1116. Min Act: -0.1700
Data Index: 3942863 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.1428. Min Act: -0.1682
Data Index: 5028869 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.1116. Min Act: -0.1700
Data Index: 3242966 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.0803. Min Act: -0.1700
Data Index: 2196570 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7053. Min Range: -7.7053
Max Act: 7.0803. Min Act: -0.1671
Data Index: 8231633 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7053. Min Range: -7.7053
Max Act: 6.9866. Min Act: -0.1700
Data Index: 8231634 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7053. Min Range: -7.7053
Max Act: 6.9553. Min Act: -0.1700
Data Index: 26126 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7053. Min Range: -7.7053
Max Act: 6.9553. Min Act: -0.1697
Data Index: 2650808 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7053. Min Range: -7.7053
Max Act: 6.9241. Min Act: -0.1700
Data Index: 5620981 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7053. Min Range: -7.7053
Max Act: 6.9241. Min Act: -0.1700
Data Index: 7132648 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19