Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3863 in Layer 7
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: 792314 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.9718. Min Act: -0.1700
Data Index: 509033 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.9405. Min Act: -0.1700
Data Index: 4117125 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.8780. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7842. Min Act: -0.1700
Data Index: 7526593 (Open Web Text)
Max Activating Token Index: 365
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: 2063561 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7842. Min Act: -0.1700
Data Index: 991975 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.8467. Min Act: -0.1700
Data Index: 5043801 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7529. Min Act: -0.1700
Data Index: 637194 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7842. Min Act: -0.1700
Data Index: 5828226 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7529. Min Act: -0.1700
Data Index: 4611927 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7216. Min Act: -0.1700
Data Index: 5659441 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7216. Min Act: -0.1700
Data Index: 6729249 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.6904. Min Act: -0.1700
Data Index: 424683 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7529. Min Act: -0.1700
Data Index: 7136198 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.6904. Min Act: -0.1700
Data Index: 911700 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.7216. Min Act: -0.1700
Data Index: 5774699 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.6904. Min Act: -0.1700
Data Index: 6652907 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.6904. Min Act: -0.1700
Data Index: 6765924 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0031. Min Range: -4.0031
Max Act: 3.6904. Min Act: -0.1700
Data Index: 830191 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19