Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4057 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.8332. Min Act: -0.1700
Data Index: 133578 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.7707. Min Act: -0.1700
Data Index: 6836715 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.7707. Min Act: -0.1700
Data Index: 242408 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.7395. Min Act: -0.1700
Data Index: 2660395 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.7082. Min Act: -0.1700
Data Index: 4231953 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6770. Min Act: -0.1700
Data Index: 5019868 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6770. Min Act: -0.1700
Data Index: 8789296 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6457. Min Act: -0.1700
Data Index: 2644634 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6457. Min Act: -0.1700
Data Index: 3450050 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6457. Min Act: -0.1700
Data Index: 5867487 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6457. Min Act: -0.1700
Data Index: 2122396 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.5832. Min Act: -0.1700
Data Index: 1497851 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6145. Min Act: -0.1700
Data Index: 2441107 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6145. Min Act: -0.1700
Data Index: 2623034 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6145. Min Act: -0.1700
Data Index: 756512 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6145. Min Act: -0.1700
Data Index: 4927563 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.6145. Min Act: -0.1700
Data Index: 889159 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.5832. Min Act: -0.1700
Data Index: 4480586 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.5832. Min Act: -0.1700
Data Index: 488354 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8332. Min Range: -4.8332
Max Act: 4.5520. Min Act: -0.1700
Data Index: 8586228 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19