Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2259 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.9339. Min Act: -0.1700
Data Index: 4669629 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.6214. Min Act: -0.1700
Data Index: 94828 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.6214. Min Act: -0.1700
Data Index: 4395783 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.5901. Min Act: -0.1700
Data Index: 7792219 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.6526. Min Act: -0.1700
Data Index: 491512 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.6214. Min Act: -0.1700
Data Index: 1599107 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.6214. Min Act: -0.1700
Data Index: 4862146 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.6214. Min Act: -0.1700
Data Index: 5399701 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.5901. Min Act: -0.1700
Data Index: 8621845 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.5901. Min Act: -0.1700
Data Index: 4064110 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.5589. Min Act: -0.1700
Data Index: 4609849 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4651. Min Act: -0.1700
Data Index: 6435078 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4339. Min Act: -0.1700
Data Index: 4917341 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4651. Min Act: -0.1700
Data Index: 4374659 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4651. Min Act: -0.1700
Data Index: 2062085 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4651. Min Act: -0.1700
Data Index: 4412819 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4651. Min Act: -0.1700
Data Index: 39386 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4651. Min Act: -0.1700
Data Index: 8525075 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4339. Min Act: -0.1700
Data Index: 6994370 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9339. Min Range: -6.9339
Max Act: 6.4026. Min Act: -0.1700
Data Index: 1907398 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19