Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.7221. Min Act: -0.1699
Data Index: 8743613 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.6596. Min Act: -0.1700
Data Index: 4511754 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.6908. Min Act: -0.1699
Data Index: 8743614 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5658. Min Act: -0.1698
Data Index: 4433633 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5346. Min Act: -0.1700
Data Index: 2683037 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5346. Min Act: -0.1700
Data Index: 6107918 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5346. Min Act: -0.1700
Data Index: 8743612 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5346. Min Act: -0.1700
Data Index: 2965172 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5346. Min Act: -0.1655
Data Index: 4511753 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5033. Min Act: -0.1698
Data Index: 2654583 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5033. Min Act: -0.1700
Data Index: 8743609 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.5033. Min Act: -0.1700
Data Index: 4559853 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.4721. Min Act: -0.1700
Data Index: 7422329 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.4721. Min Act: -0.1700
Data Index: 7185733 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.4408. Min Act: -0.1700
Data Index: 7567872 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.4721. Min Act: -0.1698
Data Index: 8743611 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.4408. Min Act: -0.1700
Data Index: 3697832 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.4408. Min Act: -0.1700
Data Index: 2132203 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.4408. Min Act: -0.1694
Data Index: 8674679 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7221. Min Range: -4.7221
Max Act: 4.4096. Min Act: -0.1697
Data Index: 1352608 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19