Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8516. Min Act: -0.1700
Data Index: 5826716 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8833. Min Act: -0.1700
Data Index: 4646108 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8357. Min Act: -0.1700
Data Index: 185217 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8198. Min Act: -0.1700
Data Index: 3140255 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7880. Min Act: -0.1700
Data Index: 2077337 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.8039. Min Act: -0.1700
Data Index: 5747761 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7880. Min Act: -0.1700
Data Index: 150750 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7720. Min Act: -0.1700
Data Index: 8569656 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7561. Min Act: -0.1700
Data Index: 2723282 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7561. Min Act: -0.1700
Data Index: 6150058 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7401. Min Act: -0.1700
Data Index: 893096 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7241. Min Act: -0.1700
Data Index: 4221928 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7241. Min Act: -0.1700
Data Index: 4577335 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7241. Min Act: -0.1700
Data Index: 4526210 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7241. Min Act: -0.1700
Data Index: 2234206 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.6921. Min Act: -0.1700
Data Index: 5043023 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.6921. Min Act: -0.1700
Data Index: 3946677 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7081. Min Act: -0.1700
Data Index: 7951686 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7081. Min Act: -0.1700
Data Index: 2229808 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8833. Min Range: -2.8833
Max Act: 2.7081. Min Act: -0.1700
Data Index: 2184617 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19