Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.5240. Min Act: -0.1700
Data Index: 2606059 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.4927. Min Act: -0.1700
Data Index: 6751616 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.4302. Min Act: -0.1700
Data Index: 3836337 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.3990. Min Act: -0.1684
Data Index: 7084963 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.3990. Min Act: -0.1700
Data Index: 9654 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.3365. Min Act: -0.1700
Data Index: 3451586 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.3052. Min Act: -0.1700
Data Index: 2867972 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.2427. Min Act: -0.1700
Data Index: 2963855 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.2427. Min Act: -0.1700
Data Index: 3787136 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.2427. Min Act: -0.1699
Data Index: 3187277 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.2115. Min Act: -0.1689
Data Index: 3794232 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.1802. Min Act: -0.1695
Data Index: 9670 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.1802. Min Act: -0.1699
Data Index: 191592 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.1177. Min Act: -0.1698
Data Index: 2483255 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.1490. Min Act: -0.1700
Data Index: 5740690 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.1490. Min Act: -0.1700
Data Index: 7124582 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.1177. Min Act: -0.1678
Data Index: 5740687 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.1177. Min Act: -0.1700
Data Index: 3022809 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.0865. Min Act: -0.1700
Data Index: 5636937 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5240. Min Range: -8.5240
Max Act: 8.0865. Min Act: -0.1700
Data Index: 5372633 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19