Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.5166. Min Act: -0.1700
Data Index: 4364106 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.4853. Min Act: -0.1700
Data Index: 8144614 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.4541. Min Act: -0.1700
Data Index: 6119095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.4541. Min Act: -0.1700
Data Index: 5574607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.4541. Min Act: -0.1700
Data Index: 2454853 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.4228. Min Act: -0.1700
Data Index: 4935734 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.4228. Min Act: -0.1700
Data Index: 4979857 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.4228. Min Act: -0.1700
Data Index: 66234 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3916. Min Act: -0.1700
Data Index: 1070405 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3603. Min Act: -0.1700
Data Index: 7281013 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3603. Min Act: -0.1700
Data Index: 4722596 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3290. Min Act: -0.1700
Data Index: 6469206 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3603. Min Act: -0.1700
Data Index: 2040656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3603. Min Act: -0.1700
Data Index: 540820 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3603. Min Act: -0.1700
Data Index: 8372919 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3603. Min Act: -0.1700
Data Index: 4962473 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3603. Min Act: -0.1700
Data Index: 1690725 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3290. Min Act: -0.1700
Data Index: 1384152 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3290. Min Act: -0.1700
Data Index: 5955224 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5166. Min Range: -4.5166
Max Act: 4.3290. Min Act: -0.1700
Data Index: 5958179 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19