Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.7874. Min Act: -0.1700
Data Index: 4001031 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.6779. Min Act: -0.1700
Data Index: 6524988 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.6153. Min Act: -0.1700
Data Index: 4319743 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.5527. Min Act: -0.1700
Data Index: 3125411 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.5214. Min Act: -0.1700
Data Index: 6092435 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.5214. Min Act: -0.1700
Data Index: 1115653 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.5214. Min Act: -0.1700
Data Index: 7702535 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.5058. Min Act: -0.1700
Data Index: 6847269 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4901. Min Act: -0.1700
Data Index: 4622931 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4588. Min Act: -0.1700
Data Index: 6782637 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4588. Min Act: -0.1700
Data Index: 7452002 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4588. Min Act: -0.1700
Data Index: 7880534 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4588. Min Act: -0.1700
Data Index: 4950342 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4588. Min Act: -0.1700
Data Index: 7442682 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4588. Min Act: -0.1700
Data Index: 7622166 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4274. Min Act: -0.1700
Data Index: 5536303 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4431. Min Act: -0.1700
Data Index: 8301427 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4431. Min Act: -0.1700
Data Index: 4131719 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4274. Min Act: -0.1700
Data Index: 3257562 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4274. Min Act: -0.1700
Data Index: 3439186 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19