Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.9310. Min Act: -0.1700
Data Index: 5774712 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.7748. Min Act: -0.1700
Data Index: 5755455 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.5248. Min Act: -0.1700
Data Index: 236108 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.3373. Min Act: -0.1700
Data Index: 6556294 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.2748. Min Act: -0.1700
Data Index: 236111 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.2123. Min Act: -0.1700
Data Index: 3923709 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.1810. Min Act: -0.1700
Data Index: 8638749 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.1185. Min Act: -0.1700
Data Index: 2223296 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.1185. Min Act: -0.1700
Data Index: 8502854 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.0873. Min Act: -0.1700
Data Index: 1885354 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9310. Min Range: -7.9310
Max Act: 7.0560. Min Act: -0.1700
Data Index: 1373354 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.9935. Min Act: -0.1700
Data Index: 4796430 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.9623. Min Act: -0.1700
Data Index: 1856898 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.9623. Min Act: -0.1700
Data Index: 7665309 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.9310. Min Act: -0.1700
Data Index: 5362738 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.8998. Min Act: -0.1700
Data Index: 5915563 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.8998. Min Act: -0.1700
Data Index: 7502201 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.8998. Min Act: -0.1700
Data Index: 5755454 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.8998. Min Act: -0.1700
Data Index: 4840817 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9310. Min Range: -7.9310
Max Act: 6.9310. Min Act: -0.1700
Data Index: 5770143 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19