Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4840 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.9231. Min Act: -0.1700
Data Index: 7820523 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.8755. Min Act: -0.1700
Data Index: 7361211 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.8438. Min Act: -0.1700
Data Index: 8638112 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.8120. Min Act: -0.1700
Data Index: 8492119 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.8120. Min Act: -0.1700
Data Index: 3047968 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7801. Min Act: -0.1700
Data Index: 5096273 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7801. Min Act: -0.1700
Data Index: 4821795 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7801. Min Act: -0.1700
Data Index: 2774256 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7801. Min Act: -0.1700
Data Index: 7516977 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7801. Min Act: -0.1700
Data Index: 1005402 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7801. Min Act: -0.1700
Data Index: 4499952 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7960. Min Act: -0.1700
Data Index: 442345 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7482. Min Act: -0.1700
Data Index: 2249934 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7642. Min Act: -0.1700
Data Index: 8135272 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7642. Min Act: -0.1700
Data Index: 4111545 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7642. Min Act: -0.1700
Data Index: 7167968 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7642. Min Act: -0.1700
Data Index: 6818717 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7642. Min Act: -0.1700
Data Index: 6046151 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7482. Min Act: -0.1700
Data Index: 179132 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9231. Min Range: -2.9231
Max Act: 2.7482. Min Act: -0.1700
Data Index: 5188848 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19