Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2339 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.8207. Min Act: -0.1700
Data Index: 5302355 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.7582. Min Act: -0.1700
Data Index: 7378793 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6332. Min Act: -0.1700
Data Index: 1805953 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6332. Min Act: -0.1700
Data Index: 3604881 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6332. Min Act: -0.1700
Data Index: 7404185 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6019. Min Act: -0.1700
Data Index: 7020839 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6019. Min Act: -0.1700
Data Index: 2866020 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6019. Min Act: -0.1700
Data Index: 7568276 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6019. Min Act: -0.1700
Data Index: 8259491 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6019. Min Act: -0.1700
Data Index: 3923698 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.5707. Min Act: -0.1700
Data Index: 3413052 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.5707. Min Act: -0.1700
Data Index: 6076490 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6019. Min Act: -0.1700
Data Index: 3112731 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6019. Min Act: -0.1700
Data Index: 8536469 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.6019. Min Act: -0.1700
Data Index: 2570112 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.5394. Min Act: -0.1700
Data Index: 1695331 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.5394. Min Act: -0.1700
Data Index: 1083904 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.5394. Min Act: -0.1700
Data Index: 2106672 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.5082. Min Act: -0.1700
Data Index: 1751228 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8207. Min Range: -4.8207
Max Act: 4.5082. Min Act: -0.1700
Data Index: 6992832 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19