Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.8850. Min Act: -0.1700
Data Index: 4254286 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.8538. Min Act: -0.1700
Data Index: 5066211 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.6350. Min Act: -0.1700
Data Index: 3928689 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.6038. Min Act: -0.1700
Data Index: 8315150 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.6350. Min Act: -0.1700
Data Index: 8354475 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.5725. Min Act: -0.1700
Data Index: 24614 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.5413. Min Act: -0.1700
Data Index: 5659402 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.5413. Min Act: -0.1700
Data Index: 1511768 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.5100. Min Act: -0.1700
Data Index: 6370873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.5100. Min Act: -0.1700
Data Index: 4549699 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.5100. Min Act: -0.1700
Data Index: 6576158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4788. Min Act: -0.1700
Data Index: 3582438 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4788. Min Act: -0.1700
Data Index: 1695259 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4788. Min Act: -0.1700
Data Index: 8451437 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4788. Min Act: -0.1700
Data Index: 1407367 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4475. Min Act: -0.1700
Data Index: 6218515 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4475. Min Act: -0.1700
Data Index: 4346664 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4788. Min Act: -0.1700
Data Index: 3951675 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4163. Min Act: -0.1700
Data Index: 6665564 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8850. Min Range: -4.8850
Max Act: 4.4163. Min Act: -0.1700
Data Index: 5422885 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19