Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0378. Min Range: -2.0378
Max Act: 2.0378. Min Act: -0.1700
Data Index: 1638987 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0378. Min Range: -2.0378
Max Act: 2.0040. Min Act: -0.1700
Data Index: 2194397 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0378. Min Range: -2.0378
Max Act: 2.0040. Min Act: -0.1700
Data Index: 5051630 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0378. Min Range: -2.0378
Max Act: 2.0040. Min Act: -0.1700
Data Index: 7215192 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0378. Min Range: -2.0378
Max Act: 2.0209. Min Act: -0.1700
Data Index: 7494457 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0378. Min Range: -2.0378
Max Act: 2.0209. Min Act: -0.1700
Data Index: 1019457 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9871. Min Act: -0.1700
Data Index: 6980429 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9871. Min Act: -0.1700
Data Index: 2259196 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9871. Min Act: -0.1700
Data Index: 5226818 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9871. Min Act: -0.1700
Data Index: 736716 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9871. Min Act: -0.1700
Data Index: 4066469 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9702. Min Act: -0.1700
Data Index: 6197702 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9871. Min Act: -0.1700
Data Index: 631040 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9702. Min Act: -0.1700
Data Index: 7781083 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9871. Min Act: -0.1700
Data Index: 7683438 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9532. Min Act: -0.1700
Data Index: 5350795 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9702. Min Act: -0.1700
Data Index: 2739843 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9702. Min Act: -0.1700
Data Index: 3817901 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9702. Min Act: -0.1700
Data Index: 4288582 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0378. Min Range: -2.0378
Max Act: 1.9702. Min Act: -0.1700
Data Index: 6656979 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19