Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3336 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.6099. Min Act: -0.1700
Data Index: 5534025 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.6099. Min Act: -0.1700
Data Index: 4954831 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.5474. Min Act: -0.1700
Data Index: 1678617 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.5786. Min Act: -0.1700
Data Index: 1130324 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.5786. Min Act: -0.1700
Data Index: 8063739 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.5474. Min Act: -0.1700
Data Index: 1909738 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.5474. Min Act: -0.1700
Data Index: 1130323 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.5161. Min Act: -0.1700
Data Index: 413644 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.5161. Min Act: -0.1700
Data Index: 6906520 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 3067006 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4536. Min Act: -0.1700
Data Index: 3841842 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 3778254 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 8740583 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 4312595 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 7855219 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 5145040 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 3871620 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 2707916 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 1470069 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6099. Min Range: -4.6099
Max Act: 4.4849. Min Act: -0.1700
Data Index: 4620318 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19