Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4293 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.9829. Min Act: -0.1700
Data Index: 5809087 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0142. Min Range: -7.0142
Max Act: 7.0142. Min Act: -0.1700
Data Index: 6109780 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.9517. Min Act: -0.1700
Data Index: 5378692 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.8892. Min Act: -0.1700
Data Index: 3133380 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.8892. Min Act: -0.1700
Data Index: 4119867 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.8579. Min Act: -0.1700
Data Index: 4854608 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.8579. Min Act: -0.1700
Data Index: 2885024 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.7954. Min Act: -0.1700
Data Index: 2412400 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.7329. Min Act: -0.1700
Data Index: 3289838 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.6392. Min Act: -0.1700
Data Index: 3439084 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.6392. Min Act: -0.1700
Data Index: 7603834 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.6704. Min Act: -0.1700
Data Index: 4479637 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.6392. Min Act: -0.1700
Data Index: 6197142 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.6392. Min Act: -0.1700
Data Index: 1808693 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.5767. Min Act: -0.1700
Data Index: 819688 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.5767. Min Act: -0.1700
Data Index: 389992 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.5454. Min Act: -0.1700
Data Index: 2707591 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.5454. Min Act: -0.1700
Data Index: 1821873 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.5454. Min Act: -0.1700
Data Index: 164983 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.5142. Min Act: -0.1700
Data Index: 8746862 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19