Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0922. Min Range: -4.0922
Max Act: 4.0922. Min Act: -0.1700
Data Index: 1693387 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0922. Min Range: -4.0922
Max Act: 4.0922. Min Act: -0.1700
Data Index: 7544546 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0922. Min Range: -4.0922
Max Act: 4.0609. Min Act: -0.1700
Data Index: 6956534 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.9984. Min Act: -0.1700
Data Index: 707193 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.9672. Min Act: -0.1700
Data Index: 4875141 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.9046. Min Act: -0.1700
Data Index: 394924 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.9046. Min Act: -0.1700
Data Index: 2722853 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.8421. Min Act: -0.1700
Data Index: 1714636 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.8421. Min Act: -0.1700
Data Index: 2774002 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.8108. Min Act: -0.1700
Data Index: 562522 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.8108. Min Act: -0.1700
Data Index: 4927160 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.8421. Min Act: -0.1700
Data Index: 315187 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.7952. Min Act: -0.1700
Data Index: 655348 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.8108. Min Act: -0.1700
Data Index: 1184996 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.7952. Min Act: -0.1700
Data Index: 3644633 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.7796. Min Act: -0.1700
Data Index: 1230253 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.8108. Min Act: -0.1700
Data Index: 26007 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.7952. Min Act: -0.1700
Data Index: 5147514 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.7796. Min Act: -0.1700
Data Index: 3038638 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0922. Min Range: -4.0922
Max Act: 3.7639. Min Act: -0.1700
Data Index: 6979361 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19