Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5111 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7509. Min Act: -0.1700
Data Index: 3163281 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6884. Min Act: -0.1700
Data Index: 7081528 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6727. Min Act: -0.1700
Data Index: 1702437 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6727. Min Act: -0.1700
Data Index: 675190 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5945. Min Act: -0.1700
Data Index: 2924304 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5788. Min Act: -0.1700
Data Index: 5064193 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5945. Min Act: -0.1700
Data Index: 1272097 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5632. Min Act: -0.1700
Data Index: 75502 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5475. Min Act: -0.1700
Data Index: 623069 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5319. Min Act: -0.1700
Data Index: 7554833 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5319. Min Act: -0.1700
Data Index: 262337 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5162. Min Act: -0.1700
Data Index: 6218852 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5319. Min Act: -0.1700
Data Index: 1868607 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5005. Min Act: -0.1700
Data Index: 8770261 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5005. Min Act: -0.1700
Data Index: 21907 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5005. Min Act: -0.1700
Data Index: 3519848 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.4692. Min Act: -0.1700
Data Index: 770772 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.4692. Min Act: -0.1700
Data Index: 3258514 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.4849. Min Act: -0.1700
Data Index: 7432242 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.4535. Min Act: -0.1700
Data Index: 3129592 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19