Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3641 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.9518. Min Act: -0.1700
Data Index: 6492195 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.9205. Min Act: -0.1700
Data Index: 8590360 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8893. Min Act: -0.1700
Data Index: 4784000 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8893. Min Act: -0.1700
Data Index: 4817841 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8580. Min Act: -0.1700
Data Index: 1916302 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8580. Min Act: -0.1700
Data Index: 984249 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8580. Min Act: -0.1700
Data Index: 2231101 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8580. Min Act: -0.1700
Data Index: 64666 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8267. Min Act: -0.1700
Data Index: 5852251 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8267. Min Act: -0.1700
Data Index: 7607448 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.8267. Min Act: -0.1700
Data Index: 1421682 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 5715015 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 5906803 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 5509975 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 4710169 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 689473 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 4994874 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 8066627 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 4999702 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9518. Min Range: -3.9518
Max Act: 3.7954. Min Act: -0.1700
Data Index: 8217659 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19