Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3327. Min Range: -5.3327
Max Act: 5.3327. Min Act: -0.1700
Data Index: 2343660 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3327. Min Range: -5.3327
Max Act: 5.2077. Min Act: -0.1700
Data Index: 7581822 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3327. Min Range: -5.3327
Max Act: 5.2390. Min Act: -0.1700
Data Index: 4404053 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3327. Min Range: -5.3327
Max Act: 5.2077. Min Act: -0.1700
Data Index: 5954931 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3327. Min Range: -5.3327
Max Act: 5.0202. Min Act: -0.1700
Data Index: 2328449 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3327. Min Range: -5.3327
Max Act: 5.0515. Min Act: -0.1700
Data Index: 2097097 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.9890. Min Act: -0.1700
Data Index: 3319589 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.9890. Min Act: -0.1700
Data Index: 3854962 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.9577. Min Act: -0.1700
Data Index: 4454711 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.9265. Min Act: -0.1700
Data Index: 7778994 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8640. Min Act: -0.1700
Data Index: 6474923 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8640. Min Act: -0.1700
Data Index: 3977014 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8952. Min Act: -0.1700
Data Index: 2445350 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8640. Min Act: -0.1700
Data Index: 4453087 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8952. Min Act: -0.1700
Data Index: 2924319 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8640. Min Act: -0.1700
Data Index: 7637844 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8327. Min Act: -0.1700
Data Index: 230582 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8327. Min Act: -0.1700
Data Index: 5907017 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8327. Min Act: -0.1700
Data Index: 2442580 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3327. Min Range: -5.3327
Max Act: 4.8327. Min Act: -0.1700
Data Index: 5830849 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19