Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5738 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.4691. Min Act: -0.1700
Data Index: 6495022 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.3128. Min Act: -0.1700
Data Index: 978767 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.3128. Min Act: -0.1700
Data Index: 8429369 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.2191. Min Act: -0.1700
Data Index: 2716417 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.1878. Min Act: -0.1700
Data Index: 7755457 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.1565. Min Act: -0.1700
Data Index: 4479444 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.1565. Min Act: -0.1700
Data Index: 6870536 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.1253. Min Act: -0.1700
Data Index: 3388051 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0940. Min Act: -0.1700
Data Index: 5675086 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0628. Min Act: -0.1700
Data Index: 3521729 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0315. Min Act: -0.1700
Data Index: 5939512 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0315. Min Act: -0.1700
Data Index: 7397625 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0003. Min Act: -0.1700
Data Index: 8028120 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0315. Min Act: -0.1700
Data Index: 7873055 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0315. Min Act: -0.1700
Data Index: 3693633 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0003. Min Act: -0.1700
Data Index: 1534853 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4691. Min Range: -4.4691
Max Act: 3.9690. Min Act: -0.1700
Data Index: 2527376 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4691. Min Range: -4.4691
Max Act: 3.9690. Min Act: -0.1700
Data Index: 46822 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4691. Min Range: -4.4691
Max Act: 3.9690. Min Act: -0.1700
Data Index: 5760973 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4691. Min Range: -4.4691
Max Act: 4.0003. Min Act: -0.1700
Data Index: 1343994 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19