Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 706 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.7968. Min Act: -0.1700
Data Index: 112148 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.7343. Min Act: -0.1700
Data Index: 4129757 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.6093. Min Act: -0.1700
Data Index: 143421 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.6093. Min Act: -0.1700
Data Index: 25590 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.5781. Min Act: -0.1700
Data Index: 4898754 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.5156. Min Act: -0.1700
Data Index: 6347963 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.5156. Min Act: -0.1700
Data Index: 3561822 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.3906. Min Act: -0.1700
Data Index: 5121687 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.3906. Min Act: -0.1700
Data Index: 3089168 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.3281. Min Act: -0.1700
Data Index: 437872 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.3281. Min Act: -0.1700
Data Index: 6793437 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.3281. Min Act: -0.1700
Data Index: 7928291 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.2968. Min Act: -0.1700
Data Index: 775048 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.2656. Min Act: -0.1700
Data Index: 7357862 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.2343. Min Act: -0.1700
Data Index: 6212970 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.2031. Min Act: -0.1700
Data Index: 1809581 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.2031. Min Act: -0.1700
Data Index: 7365331 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.1718. Min Act: -0.1700
Data Index: 6924084 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.1406. Min Act: -0.1700
Data Index: 303106 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7968. Min Range: -6.7968
Max Act: 6.1406. Min Act: -0.1700
Data Index: 6378808 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19