Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.6351. Min Act: -0.1700
Data Index: 4831158 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.5101. Min Act: -0.1700
Data Index: 553550 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.5101. Min Act: -0.1700
Data Index: 5283525 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.4164. Min Act: -0.1700
Data Index: 8675250 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.4476. Min Act: -0.1700
Data Index: 4135886 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3851. Min Act: -0.1700
Data Index: 4612239 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.4789. Min Act: -0.1700
Data Index: 3270715 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.4476. Min Act: -0.1700
Data Index: 7156475 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3851. Min Act: -0.1700
Data Index: 871229 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3851. Min Act: -0.1700
Data Index: 6947329 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3539. Min Act: -0.1700
Data Index: 1499330 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3539. Min Act: -0.1700
Data Index: 4839810 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3851. Min Act: -0.1700
Data Index: 3632036 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3539. Min Act: -0.1700
Data Index: 8098256 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3539. Min Act: -0.1700
Data Index: 1068248 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.2914. Min Act: -0.1700
Data Index: 1737274 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3226. Min Act: -0.1700
Data Index: 3115534 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.3226. Min Act: -0.1700
Data Index: 7463118 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.2914. Min Act: -0.1700
Data Index: 1683355 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6351. Min Range: -5.6351
Max Act: 5.2914. Min Act: -0.1700
Data Index: 4774668 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19