Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.6188. Min Act: -0.1700
Data Index: 3483591 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.6188. Min Act: -0.1700
Data Index: 1146684 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.5563. Min Act: -0.1700
Data Index: 7033 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.5250. Min Act: -0.1700
Data Index: 852679 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4938. Min Act: -0.1700
Data Index: 2581188 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4313. Min Act: -0.1700
Data Index: 2058730 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4313. Min Act: -0.1700
Data Index: 4379946 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4625. Min Act: -0.1700
Data Index: 2125560 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4625. Min Act: -0.1700
Data Index: 8490837 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4313. Min Act: -0.1700
Data Index: 1408327 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4000. Min Act: -0.1700
Data Index: 75451 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4000. Min Act: -0.1700
Data Index: 6388887 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4000. Min Act: -0.1700
Data Index: 4851006 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.4000. Min Act: -0.1700
Data Index: 7053674 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 2745354 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 463164 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 600647 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 1867969 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 271525 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6188. Min Range: -5.6188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 538337 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19