Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5152 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0348. Min Range: -6.0348
Max Act: 6.0348. Min Act: -0.1700
Data Index: 3370127 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.8161. Min Act: -0.1700
Data Index: 6637374 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.8161. Min Act: -0.1700
Data Index: 7522784 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.7848. Min Act: -0.1700
Data Index: 381112 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.7536. Min Act: -0.1700
Data Index: 7067608 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.7536. Min Act: -0.1700
Data Index: 5110746 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.6911. Min Act: -0.1700
Data Index: 3532389 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.6598. Min Act: -0.1700
Data Index: 3216814 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.6286. Min Act: -0.1700
Data Index: 5279161 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5973. Min Act: -0.1700
Data Index: 7702967 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5973. Min Act: -0.1700
Data Index: 6783914 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5973. Min Act: -0.1700
Data Index: 212083 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5973. Min Act: -0.1700
Data Index: 1271366 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5973. Min Act: -0.1700
Data Index: 7053726 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5661. Min Act: -0.1700
Data Index: 5465107 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5661. Min Act: -0.1700
Data Index: 1137831 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5348. Min Act: -0.1700
Data Index: 4336898 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5661. Min Act: -0.1700
Data Index: 6537680 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5036. Min Act: -0.1700
Data Index: 6548493 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0348. Min Range: -6.0348
Max Act: 5.5661. Min Act: -0.1700
Data Index: 736233 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19