Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4570 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.9782. Min Act: -0.1700
Data Index: 4946398 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.8532. Min Act: -0.1700
Data Index: 3331101 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.8532. Min Act: -0.1700
Data Index: 3100368 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.7907. Min Act: -0.1700
Data Index: 6537220 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.7907. Min Act: -0.1700
Data Index: 6212200 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.7907. Min Act: -0.1700
Data Index: 2502771 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.7282. Min Act: -0.1700
Data Index: 3159159 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.7282. Min Act: -0.1700
Data Index: 3159157 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6657. Min Act: -0.1700
Data Index: 5968005 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6657. Min Act: -0.1700
Data Index: 6594452 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6032. Min Act: -0.1700
Data Index: 114980 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6032. Min Act: -0.1700
Data Index: 3159156 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6032. Min Act: -0.1700
Data Index: 270627 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6032. Min Act: -0.1700
Data Index: 7510583 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6032. Min Act: -0.1700
Data Index: 7065412 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6032. Min Act: -0.1700
Data Index: 5031824 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.5407. Min Act: -0.1700
Data Index: 4164666 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.6032. Min Act: -0.1700
Data Index: 8236029 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.5407. Min Act: -0.1700
Data Index: 6000531 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9782. Min Range: -8.9782
Max Act: 8.5407. Min Act: -0.1700
Data Index: 4696707 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19