Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.8727. Min Act: -0.1700
Data Index: 1115402 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.8102. Min Act: -0.1700
Data Index: 6462261 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.7477. Min Act: -0.1700
Data Index: 15140 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.7164. Min Act: -0.1700
Data Index: 8265642 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.6539. Min Act: -0.1700
Data Index: 1811825 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.6539. Min Act: -0.1700
Data Index: 5766785 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.6539. Min Act: -0.1700
Data Index: 342460 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.6539. Min Act: -0.1700
Data Index: 5437681 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.6539. Min Act: -0.1700
Data Index: 3688257 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.6227. Min Act: -0.1700
Data Index: 52842 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.5914. Min Act: -0.1700
Data Index: 4733728 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.5602. Min Act: -0.1700
Data Index: 901469 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.5602. Min Act: -0.1700
Data Index: 8228323 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.5602. Min Act: -0.1700
Data Index: 8541107 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.5289. Min Act: -0.1700
Data Index: 6765995 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.5289. Min Act: -0.1700
Data Index: 3819387 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.5289. Min Act: -0.1700
Data Index: 4777605 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.5289. Min Act: -0.1700
Data Index: 8424082 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.4977. Min Act: -0.1700
Data Index: 8110744 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8727. Min Range: -4.8727
Max Act: 4.4977. Min Act: -0.1700
Data Index: 4735070 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19