Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4455 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0209. Min Range: -5.0209
Max Act: 5.0209. Min Act: -0.1700
Data Index: 6059154 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0209. Min Range: -5.0209
Max Act: 5.0209. Min Act: -0.1700
Data Index: 6925231 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.9896. Min Act: -0.1700
Data Index: 70642 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.9584. Min Act: -0.1700
Data Index: 3692438 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.9584. Min Act: -0.1700
Data Index: 846182 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.9271. Min Act: -0.1700
Data Index: 4867089 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8959. Min Act: -0.1700
Data Index: 2676178 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8646. Min Act: -0.1700
Data Index: 99333 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8959. Min Act: -0.1700
Data Index: 7999387 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8646. Min Act: -0.1700
Data Index: 902224 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8646. Min Act: -0.1700
Data Index: 239192 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8646. Min Act: -0.1700
Data Index: 620569 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8334. Min Act: -0.1700
Data Index: 8260563 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8959. Min Act: -0.1700
Data Index: 7159716 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8646. Min Act: -0.1700
Data Index: 1389061 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8646. Min Act: -0.1700
Data Index: 2456674 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8646. Min Act: -0.1700
Data Index: 154003 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8334. Min Act: -0.1700
Data Index: 1914520 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8334. Min Act: -0.1700
Data Index: 1347645 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0209. Min Range: -5.0209
Max Act: 4.8334. Min Act: -0.1700
Data Index: 6425555 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19