Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1168 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.9186. Min Act: -0.1700
Data Index: 4362580 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.8561. Min Act: -0.1700
Data Index: 1606627 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.7936. Min Act: -0.1700
Data Index: 472935 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.6998. Min Act: -0.1700
Data Index: 1147587 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.6998. Min Act: -0.1700
Data Index: 669480 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.6373. Min Act: -0.1700
Data Index: 3549051 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.6373. Min Act: -0.1700
Data Index: 6706486 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.6061. Min Act: -0.1700
Data Index: 7462129 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5748. Min Act: -0.1700
Data Index: 2586827 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5748. Min Act: -0.1700
Data Index: 2596986 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5436. Min Act: -0.1700
Data Index: 1731211 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5436. Min Act: -0.1700
Data Index: 5079665 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5436. Min Act: -0.1700
Data Index: 5620819 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5123. Min Act: -0.1700
Data Index: 6496191 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5123. Min Act: -0.1700
Data Index: 2860351 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5123. Min Act: -0.1699
Data Index: 5729526 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5123. Min Act: -0.1700
Data Index: 6011808 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5123. Min Act: -0.1700
Data Index: 8203227 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5123. Min Act: -0.1700
Data Index: 8239076 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9186. Min Range: -5.9186
Max Act: 5.5123. Min Act: -0.1700
Data Index: 8499102 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19