Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2322 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.4006. Min Act: -0.1699
Data Index: 1296633 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.3381. Min Act: -0.1700
Data Index: 8161492 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.2131. Min Act: -0.1700
Data Index: 2810859 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.1818. Min Act: -0.1700
Data Index: 6184495 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.1506. Min Act: -0.1700
Data Index: 7117476 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.1193. Min Act: -0.1700
Data Index: 4668610 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.1506. Min Act: -0.1700
Data Index: 7925768 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0881. Min Act: -0.1700
Data Index: 422143 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.1193. Min Act: -0.1700
Data Index: 422142 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.1193. Min Act: -0.1700
Data Index: 1296634 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0881. Min Act: -0.1700
Data Index: 4910256 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0568. Min Act: -0.1700
Data Index: 1963815 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0568. Min Act: -0.1692
Data Index: 4243729 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0256. Min Act: -0.1700
Data Index: 6273846 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0256. Min Act: -0.1700
Data Index: 7831698 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0256. Min Act: -0.1700
Data Index: 2010341 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0256. Min Act: -0.1700
Data Index: 3534044 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0256. Min Act: -0.1700
Data Index: 5230168 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4006. Min Range: -5.4006
Max Act: 5.0256. Min Act: -0.1700
Data Index: 525648 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4006. Min Range: -5.4006
Max Act: 4.9943. Min Act: -0.1700
Data Index: 4983398 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19