Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.9623. Min Act: -0.1700
Data Index: 6655916 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.5873. Min Act: -0.1700
Data Index: 566113 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.5248. Min Act: -0.1700
Data Index: 5364246 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.5248. Min Act: -0.1700
Data Index: 5155549 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.5248. Min Act: -0.1700
Data Index: 1736822 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.4936. Min Act: -0.1700
Data Index: 1157049 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.4623. Min Act: -0.1700
Data Index: 4261896 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.4311. Min Act: -0.1700
Data Index: 537106 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.4623. Min Act: -0.1700
Data Index: 2533413 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.3998. Min Act: -0.1700
Data Index: 1055426 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.4311. Min Act: -0.1700
Data Index: 2707967 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.3998. Min Act: -0.1700
Data Index: 1584755 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.3998. Min Act: -0.1700
Data Index: 7430064 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.3686. Min Act: -0.1700
Data Index: 7726299 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.3061. Min Act: -0.1700
Data Index: 1897345 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.3373. Min Act: -0.1700
Data Index: 3118460 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.3061. Min Act: -0.1700
Data Index: 211286 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.2748. Min Act: -0.1700
Data Index: 6339824 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.2748. Min Act: -0.1700
Data Index: 8777164 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9623. Min Range: -6.9623
Max Act: 6.2748. Min Act: -0.1700
Data Index: 61168 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19