Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.9280. Min Act: -0.1700
Data Index: 4031456 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.8967. Min Act: -0.1700
Data Index: 3667451 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.8655. Min Act: -0.1700
Data Index: 7667809 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.7405. Min Act: -0.1700
Data Index: 1121353 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.6155. Min Act: -0.1700
Data Index: 1149828 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.6155. Min Act: -0.1700
Data Index: 1587487 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.5842. Min Act: -0.1700
Data Index: 3206858 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.5530. Min Act: -0.1700
Data Index: 1902555 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.5217. Min Act: -0.1700
Data Index: 4922562 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.4592. Min Act: -0.1700
Data Index: 565849 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.4280. Min Act: -0.1700
Data Index: 573211 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.4280. Min Act: -0.1700
Data Index: 1619153 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.3967. Min Act: -0.1700
Data Index: 5435238 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.3342. Min Act: -0.1700
Data Index: 7699786 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.3342. Min Act: -0.1700
Data Index: 7781212 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.3030. Min Act: -0.1700
Data Index: 6219809 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.3030. Min Act: -0.1700
Data Index: 4808876 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.3030. Min Act: -0.1700
Data Index: 4521952 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.3030. Min Act: -0.1700
Data Index: 1997772 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9280. Min Range: -6.9280
Max Act: 6.2717. Min Act: -0.1700
Data Index: 6538287 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19