Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2036 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.6455. Min Act: -0.1700
Data Index: 3588443 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.6143. Min Act: -0.1700
Data Index: 226502 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.5830. Min Act: -0.1700
Data Index: 7455679 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.4893. Min Act: -0.1700
Data Index: 7401564 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.4893. Min Act: -0.1700
Data Index: 3297420 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.3955. Min Act: -0.1700
Data Index: 2214852 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.3955. Min Act: -0.1700
Data Index: 7827055 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.3018. Min Act: -0.1700
Data Index: 617056 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.2705. Min Act: -0.1700
Data Index: 5949571 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.2705. Min Act: -0.1700
Data Index: 8528323 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.2393. Min Act: -0.1700
Data Index: 7509626 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.2080. Min Act: -0.1700
Data Index: 6294156 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.2080. Min Act: -0.1700
Data Index: 2585985 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.2080. Min Act: -0.1700
Data Index: 2559918 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.1143. Min Act: -0.1700
Data Index: 973135 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.1143. Min Act: -0.1700
Data Index: 4269855 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.1455. Min Act: -0.1700
Data Index: 7385046 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.0518. Min Act: -0.1700
Data Index: 3570169 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.0518. Min Act: -0.1700
Data Index: 1315096 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6455. Min Range: -7.6455
Max Act: 7.0518. Min Act: -0.1700
Data Index: 542512 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19