Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2450 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.2629. Min Act: -0.1700
Data Index: 1848593 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.2316. Min Act: -0.1700
Data Index: 4639961 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.1379. Min Act: -0.1700
Data Index: 5491613 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.1379. Min Act: -0.1700
Data Index: 6799792 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.1066. Min Act: -0.1700
Data Index: 2264393 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.0441. Min Act: -0.1700
Data Index: 7381189 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.0754. Min Act: -0.1700
Data Index: 8329718 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.0129. Min Act: -0.1700
Data Index: 1458336 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.0129. Min Act: -0.1700
Data Index: 7327479 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.0129. Min Act: -0.1700
Data Index: 46996 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.0129. Min Act: -0.1700
Data Index: 6240893 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2629. Min Range: -5.2629
Max Act: 5.0129. Min Act: -0.1700
Data Index: 4851614 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2629. Min Range: -5.2629
Max Act: 4.9816. Min Act: -0.1700
Data Index: 445113 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2629. Min Range: -5.2629
Max Act: 4.9816. Min Act: -0.1700
Data Index: 1743984 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2629. Min Range: -5.2629
Max Act: 4.9816. Min Act: -0.1700
Data Index: 1442118 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2629. Min Range: -5.2629
Max Act: 4.9816. Min Act: -0.1700
Data Index: 5643873 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2629. Min Range: -5.2629
Max Act: 4.9816. Min Act: -0.1700
Data Index: 122777 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2629. Min Range: -5.2629
Max Act: 4.9504. Min Act: -0.1700
Data Index: 952539 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2629. Min Range: -5.2629
Max Act: 4.9191. Min Act: -0.1700
Data Index: 150303 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2629. Min Range: -5.2629
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4460652 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19