Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.8566. Min Act: -0.1700
Data Index: 3575906 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.6691. Min Act: -0.1700
Data Index: 2935124 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.6691. Min Act: -0.1700
Data Index: 3958900 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.4191. Min Act: -0.1700
Data Index: 6657200 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.3566. Min Act: -0.1700
Data Index: 680064 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.3254. Min Act: -0.1700
Data Index: 7609530 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.2941. Min Act: -0.1700
Data Index: 832499 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.2316. Min Act: -0.1700
Data Index: 5140767 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.2316. Min Act: -0.1700
Data Index: 6070431 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.2004. Min Act: -0.1700
Data Index: 4936341 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.1691. Min Act: -0.1700
Data Index: 680067 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.1379. Min Act: -0.1700
Data Index: 7643389 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.1379. Min Act: -0.1700
Data Index: 7157505 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.1379. Min Act: -0.1700
Data Index: 6927855 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.1066. Min Act: -0.1700
Data Index: 8362277 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.1066. Min Act: -0.1700
Data Index: 204459 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.0754. Min Act: -0.1700
Data Index: 2042149 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.0754. Min Act: -0.1700
Data Index: 2114284 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.0754. Min Act: -0.1700
Data Index: 7900161 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8566. Min Range: -7.8566
Max Act: 7.0441. Min Act: -0.1700
Data Index: 614788 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19