Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.2325. Min Act: -0.1700
Data Index: 3813176 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.2325. Min Act: -0.1700
Data Index: 3432575 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 3961073 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 1688958 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 1747165 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 17464 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1075. Min Act: -0.1700
Data Index: 2677160 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 7853327 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 3669769 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 5775883 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 6601631 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 7220701 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0137. Min Act: -0.1700
Data Index: 5626461 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0137. Min Act: -0.1700
Data Index: 93864 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0137. Min Act: -0.1700
Data Index: 4634067 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2325. Min Range: -4.2325
Max Act: 3.9824. Min Act: -0.1700
Data Index: 3395711 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0137. Min Act: -0.1700
Data Index: 5883773 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0450. Min Act: -0.1700
Data Index: 5003354 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0137. Min Act: -0.1700
Data Index: 8796126 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2325. Min Range: -4.2325
Max Act: 3.9824. Min Act: -0.1700
Data Index: 7770102 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19