Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.6480. Min Act: -0.1700
Data Index: 1360290 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.6168. Min Act: -0.1700
Data Index: 8741912 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.5855. Min Act: -0.1700
Data Index: 7986865 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.5543. Min Act: -0.1700
Data Index: 3463671 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.4605. Min Act: -0.1700
Data Index: 6259234 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.4293. Min Act: -0.1700
Data Index: 7193865 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.3668. Min Act: -0.1700
Data Index: 6574349 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.3355. Min Act: -0.1700
Data Index: 7089787 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2105. Min Act: -0.1700
Data Index: 5584435 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2105. Min Act: -0.1700
Data Index: 6103640 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.2105. Min Act: -0.1700
Data Index: 4453728 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1793. Min Act: -0.1700
Data Index: 711214 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1793. Min Act: -0.1700
Data Index: 1749021 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1793. Min Act: -0.1700
Data Index: 5323883 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1793. Min Act: -0.1700
Data Index: 682087 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1480. Min Act: -0.1700
Data Index: 7833253 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1480. Min Act: -0.1700
Data Index: 1321396 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1480. Min Act: -0.1700
Data Index: 2397515 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1480. Min Act: -0.1700
Data Index: 611138 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6480. Min Range: -5.6480
Max Act: 5.1168. Min Act: -0.1700
Data Index: 2426840 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19