Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0031. Min Range: -4.0031
Max Act: 4.0031. Min Act: -0.1700
Data Index: 5525519 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.8781. Min Act: -0.1700
Data Index: 3655302 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.8468. Min Act: -0.1700
Data Index: 5303811 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.8155. Min Act: -0.1700
Data Index: 7087840 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7686. Min Act: -0.1700
Data Index: 1490800 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7842. Min Act: -0.1700
Data Index: 7067365 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7999. Min Act: -0.1700
Data Index: 8253490 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7842. Min Act: -0.1700
Data Index: 3206576 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7686. Min Act: -0.1700
Data Index: 5468787 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7686. Min Act: -0.1700
Data Index: 1769375 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7530. Min Act: -0.1700
Data Index: 7312867 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7530. Min Act: -0.1700
Data Index: 7573181 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7373. Min Act: -0.1700
Data Index: 8066024 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7217. Min Act: -0.1700
Data Index: 4593158 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7373. Min Act: -0.1700
Data Index: 4110202 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7217. Min Act: -0.1700
Data Index: 5652579 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7217. Min Act: -0.1700
Data Index: 2361047 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7217. Min Act: -0.1700
Data Index: 5985947 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7217. Min Act: -0.1700
Data Index: 1731141 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.6748. Min Act: -0.1700
Data Index: 6469533 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19