Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2459 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.5851. Min Act: -0.1700
Data Index: 3678651 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.5851. Min Act: -0.1700
Data Index: 3934726 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.5851. Min Act: -0.1700
Data Index: 7101362 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.5226. Min Act: -0.1700
Data Index: 6248255 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.4601. Min Act: -0.1700
Data Index: 2754039 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.3976. Min Act: -0.1700
Data Index: 5340700 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.4289. Min Act: -0.1700
Data Index: 401857 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.3976. Min Act: -0.1700
Data Index: 8280532 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.3351. Min Act: -0.1700
Data Index: 2241263 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.2414. Min Act: -0.1700
Data Index: 8571993 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.2101. Min Act: -0.1700
Data Index: 1477531 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.1789. Min Act: -0.1700
Data Index: 4455823 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.1164. Min Act: -0.1700
Data Index: 4851511 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.1476. Min Act: -0.1700
Data Index: 2038221 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.1164. Min Act: -0.1700
Data Index: 7664473 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.0851. Min Act: -0.1700
Data Index: 7401877 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.0539. Min Act: -0.1700
Data Index: 6214910 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.0226. Min Act: -0.1700
Data Index: 5394047 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5851. Min Range: -7.5851
Max Act: 7.0226. Min Act: -0.1700
Data Index: 6657457 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5851. Min Range: -7.5851
Max Act: 6.9601. Min Act: -0.1700
Data Index: 3561884 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19