Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.6103. Min Act: -0.1700
Data Index: 8683519 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.5478. Min Act: -0.1700
Data Index: 1520552 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.5478. Min Act: -0.1700
Data Index: 3648824 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.5478. Min Act: -0.1699
Data Index: 2072218 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.5478. Min Act: -0.1700
Data Index: 2438839 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4853. Min Act: -0.1700
Data Index: 3203370 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4853. Min Act: -0.1700
Data Index: 6513093 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4228. Min Act: -0.1700
Data Index: 8826810 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.3603. Min Act: -0.1700
Data Index: 2316637 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4228. Min Act: -0.1700
Data Index: 8700711 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4228. Min Act: -0.1700
Data Index: 4232834 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4228. Min Act: -0.1700
Data Index: 4232828 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4228. Min Act: -0.1700
Data Index: 3860288 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4228. Min Act: -0.1700
Data Index: 2013408 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.3603. Min Act: -0.1689
Data Index: 1264548 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.3603. Min Act: -0.1700
Data Index: 2066900 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.3603. Min Act: -0.1700
Data Index: 3418403 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.3603. Min Act: -0.1700
Data Index: 4886411 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.4228. Min Act: -0.1700
Data Index: 4084841 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6103. Min Range: -10.6103
Max Act: 10.3603. Min Act: -0.1700
Data Index: 714462 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19