Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1694 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.9624. Min Act: -0.1700
Data Index: 7461513 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.9311. Min Act: -0.1700
Data Index: 7498619 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.8999. Min Act: -0.1700
Data Index: 5738520 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.8686. Min Act: -0.1700
Data Index: 1173370 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.8373. Min Act: -0.1700
Data Index: 1926912 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.8061. Min Act: -0.1700
Data Index: 332535 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7748. Min Act: -0.1700
Data Index: 3154109 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.8061. Min Act: -0.1700
Data Index: 2070832 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7748. Min Act: -0.1700
Data Index: 4387043 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7748. Min Act: -0.1700
Data Index: 1512699 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7748. Min Act: -0.1700
Data Index: 2010758 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7122. Min Act: -0.1700
Data Index: 5245183 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7435. Min Act: -0.1700
Data Index: 3236191 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7435. Min Act: -0.1700
Data Index: 3410951 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7435. Min Act: -0.1700
Data Index: 2040125 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7122. Min Act: -0.1700
Data Index: 5311097 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7122. Min Act: -0.1700
Data Index: 4704143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7122. Min Act: -0.1700
Data Index: 6438858 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7122. Min Act: -0.1700
Data Index: 2899240 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9624. Min Range: -3.9624
Max Act: 3.7435. Min Act: -0.1700
Data Index: 4324330 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19