Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3977. Min Range: -9.3977
Max Act: 9.3977. Min Act: -0.1700
Data Index: 5987971 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3977. Min Range: -9.3977
Max Act: 9.3352. Min Act: -0.1700
Data Index: 1111192 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3977. Min Range: -9.3977
Max Act: 9.0852. Min Act: -0.1700
Data Index: 45148 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.8977. Min Act: -0.1700
Data Index: 3445941 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.8352. Min Act: -0.1700
Data Index: 2909241 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.8352. Min Act: -0.1700
Data Index: 2622028 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.7727. Min Act: -0.1700
Data Index: 315676 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.5852. Min Act: -0.1700
Data Index: 5877137 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.7102. Min Act: -0.1700
Data Index: 2156755 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.7102. Min Act: -0.1700
Data Index: 2909238 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.6477. Min Act: -0.1700
Data Index: 1106989 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.6477. Min Act: -0.1700
Data Index: 7826707 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.5852. Min Act: -0.1700
Data Index: 5987963 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.4602. Min Act: -0.1700
Data Index: 4029654 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.5227. Min Act: -0.1700
Data Index: 1006506 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.5852. Min Act: -0.1700
Data Index: 4029659 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.4602. Min Act: -0.1700
Data Index: 6737282 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.4602. Min Act: -0.1700
Data Index: 1914823 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.3977. Min Act: -0.1700
Data Index: 2529510 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3977. Min Range: -9.3977
Max Act: 8.4602. Min Act: -0.1700
Data Index: 3656777 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19