Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0556. Min Range: -1.0556
Max Act: 1.0556. Min Act: -0.1700
Data Index: 3681759 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0556. Min Range: -1.0556
Max Act: 1.0207. Min Act: -0.1700
Data Index: 3839989 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0556. Min Range: -1.0556
Max Act: 1.0207. Min Act: -0.1700
Data Index: 626140 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0556. Min Range: -1.0556
Max Act: 1.0033. Min Act: -0.1700
Data Index: 1202181 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0556. Min Range: -1.0556
Max Act: 1.0207. Min Act: -0.1700
Data Index: 3145988 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9860. Min Act: -0.1700
Data Index: 1203982 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9860. Min Act: -0.1700
Data Index: 5052796 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9860. Min Act: -0.1700
Data Index: 2301458 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9860. Min Act: -0.1700
Data Index: 8070784 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9687. Min Act: -0.1700
Data Index: 2102367 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9687. Min Act: -0.1700
Data Index: 1357771 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9687. Min Act: -0.1700
Data Index: 3634725 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9860. Min Act: -0.1700
Data Index: 7785561 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9687. Min Act: -0.1700
Data Index: 5482658 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9687. Min Act: -0.1700
Data Index: 504363 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9687. Min Act: -0.1700
Data Index: 5125578 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9687. Min Act: -0.1700
Data Index: 5086504 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9687. Min Act: -0.1700
Data Index: 4136080 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9342. Min Act: -0.1700
Data Index: 3905931 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0556. Min Range: -1.0556
Max Act: 0.9514. Min Act: -0.1700
Data Index: 3996117 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19