Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4617 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4768. Min Range: -9.4768
Max Act: 9.4768. Min Act: -0.1700
Data Index: 8423243 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4768. Min Range: -9.4768
Max Act: 9.2268. Min Act: -0.1700
Data Index: 7256613 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4768. Min Range: -9.4768
Max Act: 9.1643. Min Act: -0.1700
Data Index: 2264380 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4768. Min Range: -9.4768
Max Act: 9.1643. Min Act: -0.1700
Data Index: 3719689 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4768. Min Range: -9.4768
Max Act: 9.1018. Min Act: -0.1700
Data Index: 8016567 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4768. Min Range: -9.4768
Max Act: 9.1018. Min Act: -0.1700
Data Index: 2948715 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.9768. Min Act: -0.1700
Data Index: 5070219 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.9768. Min Act: -0.1700
Data Index: 1861187 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.9768. Min Act: -0.1700
Data Index: 355204 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.9768. Min Act: -0.1700
Data Index: 1831595 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.9143. Min Act: -0.1700
Data Index: 8459423 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.9143. Min Act: -0.1700
Data Index: 8121627 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.9143. Min Act: -0.1700
Data Index: 4588310 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.9768. Min Act: -0.1700
Data Index: 5694575 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.8518. Min Act: -0.1700
Data Index: 7889540 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.8518. Min Act: -0.1700
Data Index: 5473045 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.8518. Min Act: -0.1700
Data Index: 1110954 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.8518. Min Act: -0.1700
Data Index: 1808938 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.8518. Min Act: -0.1700
Data Index: 2508659 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4768. Min Range: -9.4768
Max Act: 8.8518. Min Act: -0.1700
Data Index: 5002628 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19