Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 692 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.5487. Min Act: -0.1700
Data Index: 2404371 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.3925. Min Act: -0.1700
Data Index: 4705576 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.2675. Min Act: -0.1700
Data Index: 8690553 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.2362. Min Act: -0.1700
Data Index: 7863391 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.2362. Min Act: -0.1700
Data Index: 3827635 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.2050. Min Act: -0.1700
Data Index: 4255959 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.1737. Min Act: -0.1700
Data Index: 4131009 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.1737. Min Act: -0.1700
Data Index: 1564820 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.2050. Min Act: -0.1700
Data Index: 6750694 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.1737. Min Act: -0.1700
Data Index: 3111018 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.1425. Min Act: -0.1700
Data Index: 7104899 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.0799. Min Act: -0.1700
Data Index: 3856359 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.1112. Min Act: -0.1700
Data Index: 6491094 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.1425. Min Act: -0.1700
Data Index: 5899874 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.1112. Min Act: -0.1700
Data Index: 6336864 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.0799. Min Act: -0.1700
Data Index: 8294619 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.0799. Min Act: -0.1700
Data Index: 1923250 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.0487. Min Act: -0.1700
Data Index: 7817648 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.0174. Min Act: -0.1700
Data Index: 1862031 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5487. Min Range: -4.5487
Max Act: 4.0487. Min Act: -0.1700
Data Index: 6976504 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19