Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3988 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.5003. Min Act: -0.1700
Data Index: 8435780 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.5003. Min Act: -0.1700
Data Index: 6601233 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.3753. Min Act: -0.1700
Data Index: 479414 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.3128. Min Act: -0.1700
Data Index: 3981937 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.1878. Min Act: -0.1700
Data Index: 2752208 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.1253. Min Act: -0.1700
Data Index: 5287083 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.1253. Min Act: -0.1700
Data Index: 2014675 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.1253. Min Act: -0.1700
Data Index: 4047875 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.0628. Min Act: -0.1700
Data Index: 2653655 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5003. Min Range: -8.5003
Max Act: 8.0003. Min Act: -0.1700
Data Index: 2179549 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.9378. Min Act: -0.1700
Data Index: 279513 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.8753. Min Act: -0.1700
Data Index: 5454037 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.9378. Min Act: -0.1700
Data Index: 2603184 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.8753. Min Act: -0.1700
Data Index: 1328942 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.8128. Min Act: -0.1700
Data Index: 4728218 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.8128. Min Act: -0.1700
Data Index: 8137977 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.8128. Min Act: -0.1700
Data Index: 252802 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.8128. Min Act: -0.1700
Data Index: 6943752 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.7503. Min Act: -0.1700
Data Index: 1814626 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5003. Min Range: -8.5003
Max Act: 7.7503. Min Act: -0.1700
Data Index: 1617988 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19