Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5370 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6099. Min Range: -10.6099
Max Act: 10.6099. Min Act: -0.1700
Data Index: 2996060 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6099. Min Range: -10.6099
Max Act: 10.3599. Min Act: -0.1700
Data Index: 4996806 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6099. Min Range: -10.6099
Max Act: 10.2974. Min Act: -0.1700
Data Index: 5837808 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6099. Min Range: -10.6099
Max Act: 10.3599. Min Act: -0.1700
Data Index: 6795720 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6099. Min Range: -10.6099
Max Act: 10.2349. Min Act: -0.1700
Data Index: 7333761 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6099. Min Range: -10.6099
Max Act: 10.1099. Min Act: -0.1700
Data Index: 1055845 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.9849. Min Act: -0.1700
Data Index: 6922234 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.9849. Min Act: -0.1700
Data Index: 4936408 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.9849. Min Act: -0.1700
Data Index: 1836432 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.9849. Min Act: -0.1700
Data Index: 63124 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.9849. Min Act: -0.1700
Data Index: 1895995 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.9849. Min Act: -0.1700
Data Index: 2587208 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.9224. Min Act: -0.1700
Data Index: 5625336 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.8599. Min Act: -0.1700
Data Index: 36640 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.8599. Min Act: -0.1700
Data Index: 6832039 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.8599. Min Act: -0.1700
Data Index: 206703 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.8599. Min Act: -0.1700
Data Index: 7883581 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.8599. Min Act: -0.1700
Data Index: 659461 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.8599. Min Act: -0.1700
Data Index: 4281128 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6099. Min Range: -10.6099
Max Act: 9.8599. Min Act: -0.1700
Data Index: 1678777 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19