Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1344 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.8905. Min Act: -0.1700
Data Index: 1782502 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.8593. Min Act: -0.1700
Data Index: 1782501 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.8280. Min Act: -0.1700
Data Index: 1782497 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.6405. Min Act: -0.1700
Data Index: 1782503 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.5780. Min Act: -0.1700
Data Index: 1782499 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.5155. Min Act: -0.1700
Data Index: 1782498 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.4843. Min Act: -0.1700
Data Index: 1782500 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.4530. Min Act: -0.1700
Data Index: 3763793 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.3593. Min Act: -0.1700
Data Index: 4891353 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2968. Min Act: -0.1700
Data Index: 6552699 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2968. Min Act: -0.1700
Data Index: 5904947 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2968. Min Act: -0.1700
Data Index: 239592 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2655. Min Act: -0.1700
Data Index: 7087354 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2343. Min Act: -0.1700
Data Index: 60300 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2343. Min Act: -0.1700
Data Index: 2289442 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2030. Min Act: -0.1700
Data Index: 8421119 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2030. Min Act: -0.1700
Data Index: 2814261 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2030. Min Act: -0.1700
Data Index: 6741061 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.2343. Min Act: -0.1700
Data Index: 3143678 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8905. Min Range: -6.8905
Max Act: 6.1405. Min Act: -0.1700
Data Index: 6552702 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19