Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5952 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.9224. Min Act: -0.1700
Data Index: 1422612 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.7349. Min Act: -0.1700
Data Index: 4439785 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.7349. Min Act: -0.1700
Data Index: 1653669 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.6724. Min Act: -0.1700
Data Index: 4743553 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.6412. Min Act: -0.1700
Data Index: 5028649 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.6412. Min Act: -0.1700
Data Index: 7165272 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.6412. Min Act: -0.1700
Data Index: 3476891 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.6099. Min Act: -0.1700
Data Index: 5816851 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.5787. Min Act: -0.1700
Data Index: 879369 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.5787. Min Act: -0.1700
Data Index: 5370001 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.5474. Min Act: -0.1700
Data Index: 547076 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.5474. Min Act: -0.1700
Data Index: 7073018 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.5162. Min Act: -0.1700
Data Index: 8646413 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.5162. Min Act: -0.1700
Data Index: 6157085 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.4537. Min Act: -0.1700
Data Index: 6863600 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.4849. Min Act: -0.1700
Data Index: 879368 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.4537. Min Act: -0.1700
Data Index: 8441687 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.4224. Min Act: -0.1700
Data Index: 6624634 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.4537. Min Act: -0.1700
Data Index: 3477221 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9224. Min Range: -6.9224
Max Act: 6.3912. Min Act: -0.1700
Data Index: 2996448 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19