Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0095. Min Range: -4.0095
Max Act: 4.0095. Min Act: -0.1700
Data Index: 2709234 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6968. Min Act: -0.1700
Data Index: 2366141 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6342. Min Act: -0.1700
Data Index: 1286517 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6655. Min Act: -0.1700
Data Index: 3513139 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6655. Min Act: -0.1700
Data Index: 8507421 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6342. Min Act: -0.1700
Data Index: 4912498 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6342. Min Act: -0.1700
Data Index: 315036 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6186. Min Act: -0.1700
Data Index: 170283 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5873. Min Act: -0.1700
Data Index: 7158971 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5873. Min Act: -0.1700
Data Index: 2430899 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6029. Min Act: -0.1700
Data Index: 2128336 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5716. Min Act: -0.1700
Data Index: 7521168 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.6029. Min Act: -0.1700
Data Index: 5857592 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5873. Min Act: -0.1700
Data Index: 3780010 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5716. Min Act: -0.1700
Data Index: 4605676 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5716. Min Act: -0.1700
Data Index: 5082894 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5559. Min Act: -0.1700
Data Index: 7188631 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5716. Min Act: -0.1700
Data Index: 1785614 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5559. Min Act: -0.1700
Data Index: 2815449 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0095. Min Range: -4.0095
Max Act: 3.5559. Min Act: -0.1700
Data Index: 5255051 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19