Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 1072617 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1718. Min Act: -0.1700
Data Index: 3058661 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1406. Min Act: -0.1700
Data Index: 6999425 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1406. Min Act: -0.1700
Data Index: 5214091 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1406. Min Act: -0.1700
Data Index: 1396482 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1093. Min Act: -0.1700
Data Index: 8302738 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1093. Min Act: -0.1700
Data Index: 2900931 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0781. Min Act: -0.1700
Data Index: 4927475 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0781. Min Act: -0.1700
Data Index: 5658312 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0468. Min Act: -0.1700
Data Index: 6083361 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0468. Min Act: -0.1700
Data Index: 2028707 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 6622957 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9843. Min Act: -0.1700
Data Index: 3426436 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 7709195 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9843. Min Act: -0.1700
Data Index: 5872717 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 4167219 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 4559814 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9218. Min Act: -0.1700
Data Index: 6098662 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9218. Min Act: -0.1700
Data Index: 5022219 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9218. Min Act: -0.1700
Data Index: 3006818 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19