Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.5084. Min Act: -0.1700
Data Index: 8160261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.5084. Min Act: -0.1700
Data Index: 2032708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4772. Min Act: -0.1700
Data Index: 5007005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.5397. Min Act: -0.1700
Data Index: 3166491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4772. Min Act: -0.1700
Data Index: 5982466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4772. Min Act: -0.1700
Data Index: 7435991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4772. Min Act: -0.1700
Data Index: 585820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4772. Min Act: -0.1700
Data Index: 2982666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4772. Min Act: -0.1700
Data Index: 1766546 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4772. Min Act: -0.1700
Data Index: 930277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4772. Min Act: -0.1700
Data Index: 8088669 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4459. Min Act: -0.1700
Data Index: 507480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4459. Min Act: -0.1700
Data Index: 1571860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4147. Min Act: -0.1700
Data Index: 2981067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4459. Min Act: -0.1700
Data Index: 5574661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4459. Min Act: -0.1700
Data Index: 4207171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4459. Min Act: -0.1700
Data Index: 3969783 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4147. Min Act: -0.1700
Data Index: 525929 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4459. Min Act: -0.1700
Data Index: 5815493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5397. Min Range: -4.5397
Max Act: 4.4459. Min Act: -0.1700
Data Index: 769805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19