Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4106 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.3331. Min Act: -0.1700
Data Index: 2947605 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.3019. Min Act: -0.1700
Data Index: 150258 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.2706. Min Act: -0.1700
Data Index: 2515751 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.2706. Min Act: -0.1700
Data Index: 3086599 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.2394. Min Act: -0.1700
Data Index: 8418273 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.2081. Min Act: -0.1700
Data Index: 5594657 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1768. Min Act: -0.1700
Data Index: 1894057 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1768. Min Act: -0.1700
Data Index: 973386 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1768. Min Act: -0.1700
Data Index: 6543996 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1768. Min Act: -0.1700
Data Index: 5564389 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1768. Min Act: -0.1700
Data Index: 4285839 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1456. Min Act: -0.1700
Data Index: 4210739 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1768. Min Act: -0.1700
Data Index: 2167415 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1456. Min Act: -0.1700
Data Index: 5490905 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1456. Min Act: -0.1700
Data Index: 2892650 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1456. Min Act: -0.1700
Data Index: 2721807 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1456. Min Act: -0.1700
Data Index: 372279 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1456. Min Act: -0.1700
Data Index: 4110578 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1456. Min Act: -0.1700
Data Index: 8153402 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3331. Min Range: -4.3331
Max Act: 4.1456. Min Act: -0.1700
Data Index: 3480398 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19