Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1061 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.3600. Min Act: -0.1700
Data Index: 8165120 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.2350. Min Act: -0.1700
Data Index: 892383 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.2663. Min Act: -0.1700
Data Index: 7301917 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.1725. Min Act: -0.1700
Data Index: 5040636 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.1725. Min Act: -0.1700
Data Index: 606860 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.1413. Min Act: -0.1700
Data Index: 3647116 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.0788. Min Act: -0.1700
Data Index: 510592 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.0788. Min Act: -0.1700
Data Index: 4658264 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.0475. Min Act: -0.1700
Data Index: 714238 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.0475. Min Act: -0.1700
Data Index: 3343356 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3600. Min Range: -7.3600
Max Act: 7.0163. Min Act: -0.1700
Data Index: 2276592 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.9538. Min Act: -0.1700
Data Index: 3403911 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.9225. Min Act: -0.1700
Data Index: 371706 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.9225. Min Act: -0.1700
Data Index: 8680368 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.8913. Min Act: -0.1700
Data Index: 1552538 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.9538. Min Act: -0.1700
Data Index: 1957758 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.8913. Min Act: -0.1700
Data Index: 5262001 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.8600. Min Act: -0.1700
Data Index: 5836945 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.9225. Min Act: -0.1700
Data Index: 4738991 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3600. Min Range: -7.3600
Max Act: 6.8913. Min Act: -0.1700
Data Index: 4847371 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19