Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 676 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.6297. Min Act: -0.1700
Data Index: 3560345 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.5359. Min Act: -0.1700
Data Index: 4127828 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.4422. Min Act: -0.1700
Data Index: 5809873 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.4422. Min Act: -0.1700
Data Index: 1767402 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.4109. Min Act: -0.1700
Data Index: 2727262 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3797. Min Act: -0.1700
Data Index: 611909 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.3172. Min Act: -0.1700
Data Index: 3542613 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2859. Min Act: -0.1700
Data Index: 6378623 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.1922. Min Act: -0.1700
Data Index: 6477510 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2234. Min Act: -0.1700
Data Index: 1973957 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2234. Min Act: -0.1700
Data Index: 4034120 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2234. Min Act: -0.1700
Data Index: 6047973 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.2234. Min Act: -0.1700
Data Index: 274453 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.1609. Min Act: -0.1700
Data Index: 5913987 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.1297. Min Act: -0.1700
Data Index: 3513558 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.0984. Min Act: -0.1700
Data Index: 6446860 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.0984. Min Act: -0.1700
Data Index: 1807736 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.0359. Min Act: -0.1700
Data Index: 8598703 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.0984. Min Act: -0.1700
Data Index: 1767400 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6297. Min Range: -7.6297
Max Act: 7.0359. Min Act: -0.1700
Data Index: 7395974 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19