Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.5704. Min Act: -0.1700
Data Index: 4016223 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.4454. Min Act: -0.1700
Data Index: 6017803 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.2892. Min Act: -0.1700
Data Index: 3533478 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.3204. Min Act: -0.1700
Data Index: 4323425 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.2892. Min Act: -0.1700
Data Index: 1731351 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.2579. Min Act: -0.1700
Data Index: 4071686 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.1954. Min Act: -0.1700
Data Index: 1863073 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.1642. Min Act: -0.1700
Data Index: 2755942 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.1642. Min Act: -0.1700
Data Index: 3195356 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.1954. Min Act: -0.1700
Data Index: 5418178 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.1329. Min Act: -0.1700
Data Index: 6572979 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.0392. Min Act: -0.1700
Data Index: 2857761 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.0392. Min Act: -0.1700
Data Index: 6586672 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.0079. Min Act: -0.1700
Data Index: 7448162 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.0392. Min Act: -0.1700
Data Index: 7704 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.1017. Min Act: -0.1700
Data Index: 8192933 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.0392. Min Act: -0.1700
Data Index: 8233243 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.0079. Min Act: -0.1700
Data Index: 2803515 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.0079. Min Act: -0.1700
Data Index: 4819527 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5704. Min Range: -6.5704
Max Act: 6.0079. Min Act: -0.1700
Data Index: 398957 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19