Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8066. Min Range: -6.8066
Max Act: 6.8066. Min Act: -0.1700
Data Index: 6590653 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8066. Min Range: -6.8066
Max Act: 6.7753. Min Act: -0.1700
Data Index: 7936813 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8066. Min Range: -6.8066
Max Act: 6.4628. Min Act: -0.1700
Data Index: 4193535 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8066. Min Range: -6.8066
Max Act: 6.4003. Min Act: -0.1700
Data Index: 1116479 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8066. Min Range: -6.8066
Max Act: 6.2753. Min Act: -0.1700
Data Index: 2146623 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8066. Min Range: -6.8066
Max Act: 6.1816. Min Act: -0.1700
Data Index: 667767 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8066. Min Range: -6.8066
Max Act: 6.0253. Min Act: -0.1700
Data Index: 7067935 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8066. Min Range: -6.8066
Max Act: 6.0253. Min Act: -0.1700
Data Index: 3445880 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.9941. Min Act: -0.1700
Data Index: 667765 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.9628. Min Act: -0.1700
Data Index: 1178956 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.9628. Min Act: -0.1700
Data Index: 667755 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.9316. Min Act: -0.1700
Data Index: 2241289 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.9003. Min Act: -0.1700
Data Index: 667762 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.9316. Min Act: -0.1700
Data Index: 667752 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.8378. Min Act: -0.1700
Data Index: 8023323 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.8378. Min Act: -0.1700
Data Index: 4781342 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.8378. Min Act: -0.1700
Data Index: 8038627 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.8378. Min Act: -0.1700
Data Index: 667754 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.8378. Min Act: -0.1700
Data Index: 3291788 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8066. Min Range: -6.8066
Max Act: 5.8066. Min Act: -0.1700
Data Index: 8730764 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19