Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1638 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.4568. Min Act: -0.1700
Data Index: 3345492 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.4724. Min Act: -0.1700
Data Index: 4526022 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.4568. Min Act: -0.1700
Data Index: 7113046 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.4568. Min Act: -0.1700
Data Index: 3740805 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.3941. Min Act: -0.1700
Data Index: 4619816 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.3313. Min Act: -0.1700
Data Index: 92137 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.3156. Min Act: -0.1700
Data Index: 1146307 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2999. Min Act: -0.1700
Data Index: 600188 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2999. Min Act: -0.1700
Data Index: 1135173 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2999. Min Act: -0.1700
Data Index: 899839 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2842. Min Act: -0.1700
Data Index: 3992272 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2842. Min Act: -0.1700
Data Index: 3292017 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2685. Min Act: -0.1700
Data Index: 6723953 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2528. Min Act: -0.1700
Data Index: 1855400 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2214. Min Act: -0.1700
Data Index: 5237323 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2371. Min Act: -0.1700
Data Index: 1282631 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2371. Min Act: -0.1700
Data Index: 574196 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2371. Min Act: -0.1700
Data Index: 151960 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2685. Min Act: -0.1700
Data Index: 6973999 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4724. Min Range: -3.4724
Max Act: 3.2528. Min Act: -0.1700
Data Index: 2433865 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19