Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.4606. Min Act: -0.1700
Data Index: 7462338 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.4443. Min Act: -0.1700
Data Index: 8010001 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.4443. Min Act: -0.1700
Data Index: 5849187 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.4280. Min Act: -0.1700
Data Index: 3922819 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.4117. Min Act: -0.1700
Data Index: 2432224 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3954. Min Act: -0.1700
Data Index: 1710544 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3791. Min Act: -0.1700
Data Index: 1700817 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3627. Min Act: -0.1700
Data Index: 478565 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3299. Min Act: -0.1700
Data Index: 4984552 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3135. Min Act: -0.1700
Data Index: 1971720 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3299. Min Act: -0.1700
Data Index: 4308178 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3299. Min Act: -0.1700
Data Index: 479815 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3299. Min Act: -0.1700
Data Index: 4382168 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3135. Min Act: -0.1700
Data Index: 4517368 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3135. Min Act: -0.1700
Data Index: 62013 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3135. Min Act: -0.1700
Data Index: 5549266 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.2971. Min Act: -0.1700
Data Index: 1053526 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3135. Min Act: -0.1700
Data Index: 5934253 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.3135. Min Act: -0.1700
Data Index: 4447682 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4606. Min Range: -2.4606
Max Act: 2.2971. Min Act: -0.1700
Data Index: 1981322 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19