Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0842. Min Range: -3.0842
Max Act: 3.0842. Min Act: -0.1700
Data Index: 4225270 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0842. Min Range: -3.0842
Max Act: 3.0684. Min Act: -0.1700
Data Index: 77632 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0842. Min Range: -3.0842
Max Act: 3.0527. Min Act: -0.1700
Data Index: 4772589 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0842. Min Range: -3.0842
Max Act: 3.0211. Min Act: -0.1700
Data Index: 3976535 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9895. Min Act: -0.1700
Data Index: 1796933 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9895. Min Act: -0.1700
Data Index: 1746579 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9737. Min Act: -0.1700
Data Index: 2791567 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9737. Min Act: -0.1700
Data Index: 6246833 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9579. Min Act: -0.1700
Data Index: 7896258 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9420. Min Act: -0.1700
Data Index: 5528569 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9579. Min Act: -0.1700
Data Index: 4978551 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9420. Min Act: -0.1700
Data Index: 672189 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9579. Min Act: -0.1700
Data Index: 5594346 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9420. Min Act: -0.1700
Data Index: 7620885 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9420. Min Act: -0.1700
Data Index: 4795769 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9420. Min Act: -0.1700
Data Index: 3468018 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9579. Min Act: -0.1700
Data Index: 7065854 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9262. Min Act: -0.1700
Data Index: 2394762 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9420. Min Act: -0.1700
Data Index: 2480701 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0842. Min Range: -3.0842
Max Act: 2.9103. Min Act: -0.1700
Data Index: 5009948 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19