Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5438 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0233. Min Range: -7.0233
Max Act: 7.0233. Min Act: -0.1700
Data Index: 7453940 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0233. Min Range: -7.0233
Max Act: 7.0233. Min Act: -0.1700
Data Index: 5276878 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.9920. Min Act: -0.1700
Data Index: 3984448 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.9920. Min Act: -0.1700
Data Index: 6431840 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.9608. Min Act: -0.1700
Data Index: 5373888 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.9295. Min Act: -0.1700
Data Index: 4594667 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.8670. Min Act: -0.1700
Data Index: 566151 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.8670. Min Act: -0.1700
Data Index: 1995663 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.8670. Min Act: -0.1700
Data Index: 7274211 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.8358. Min Act: -0.1700
Data Index: 3234633 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.7733. Min Act: -0.1700
Data Index: 1706206 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.8045. Min Act: -0.1700
Data Index: 4716837 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.7420. Min Act: -0.1700
Data Index: 7908325 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.7420. Min Act: -0.1700
Data Index: 6504599 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.7420. Min Act: -0.1700
Data Index: 2702952 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.7420. Min Act: -0.1700
Data Index: 1769748 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.7108. Min Act: -0.1700
Data Index: 5682829 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.6795. Min Act: -0.1700
Data Index: 5641430 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.6795. Min Act: -0.1700
Data Index: 7460649 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0233. Min Range: -7.0233
Max Act: 6.6483. Min Act: -0.1700
Data Index: 1546273 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19