Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3860 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.6207. Min Act: -0.1700
Data Index: 4030088 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.6207. Min Act: -0.1700
Data Index: 6262798 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5894. Min Act: -0.1700
Data Index: 1764104 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5894. Min Act: -0.1700
Data Index: 7135423 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5894. Min Act: -0.1700
Data Index: 5393134 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5581. Min Act: -0.1700
Data Index: 591319 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5581. Min Act: -0.1700
Data Index: 1672693 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5581. Min Act: -0.1700
Data Index: 6212040 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5268. Min Act: -0.1700
Data Index: 7111607 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5268. Min Act: -0.1700
Data Index: 6212048 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5268. Min Act: -0.1700
Data Index: 591316 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5268. Min Act: -0.1700
Data Index: 430680 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5268. Min Act: -0.1700
Data Index: 8244621 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5268. Min Act: -0.1700
Data Index: 7361843 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5581. Min Act: -0.1700
Data Index: 6301217 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5268. Min Act: -0.1700
Data Index: 7222581 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.4955. Min Act: -0.1700
Data Index: 7002663 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.5268. Min Act: -0.1700
Data Index: 4520413 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.4955. Min Act: -0.1700
Data Index: 7135427 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6207. Min Range: -3.6207
Max Act: 3.4955. Min Act: -0.1700
Data Index: 591315 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19