Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4231 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.8110. Min Act: -0.1700
Data Index: 2272228 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.5297. Min Act: -0.1700
Data Index: 578831 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.5610. Min Act: -0.1700
Data Index: 5756520 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4985. Min Act: -0.1700
Data Index: 119186 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4985. Min Act: -0.1700
Data Index: 5769021 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4672. Min Act: -0.1700
Data Index: 1186997 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4672. Min Act: -0.1700
Data Index: 7019034 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4985. Min Act: -0.1700
Data Index: 4928305 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4047. Min Act: -0.1700
Data Index: 4554582 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3735. Min Act: -0.1700
Data Index: 6276707 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4047. Min Act: -0.1700
Data Index: 433923 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4047. Min Act: -0.1700
Data Index: 5388330 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4047. Min Act: -0.1700
Data Index: 8087915 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3735. Min Act: -0.1700
Data Index: 6562469 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3422. Min Act: -0.1700
Data Index: 154176 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3422. Min Act: -0.1700
Data Index: 501403 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3422. Min Act: -0.1700
Data Index: 371096 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3422. Min Act: -0.1700
Data Index: 36598 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3422. Min Act: -0.1700
Data Index: 5109217 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3422. Min Act: -0.1700
Data Index: 775388 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19