Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3962. Min Act: -0.1700
Data Index: 5235419 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3492. Min Act: -0.1700
Data Index: 2612294 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3492. Min Act: -0.1700
Data Index: 7139580 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3335. Min Act: -0.1700
Data Index: 7973405 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3335. Min Act: -0.1700
Data Index: 4395478 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3335. Min Act: -0.1700
Data Index: 6532978 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3178. Min Act: -0.1700
Data Index: 4026993 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3178. Min Act: -0.1700
Data Index: 6358316 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.3021. Min Act: -0.1700
Data Index: 4141928 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2864. Min Act: -0.1700
Data Index: 2590073 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2864. Min Act: -0.1700
Data Index: 5787604 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2864. Min Act: -0.1700
Data Index: 8168853 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2864. Min Act: -0.1700
Data Index: 3255579 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2707. Min Act: -0.1700
Data Index: 4939924 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2707. Min Act: -0.1700
Data Index: 7123454 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2707. Min Act: -0.1700
Data Index: 1330428 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2707. Min Act: -0.1700
Data Index: 1487832 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2707. Min Act: -0.1700
Data Index: 4461826 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2550. Min Act: -0.1700
Data Index: 2616817 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3962. Min Range: -3.3962
Max Act: 3.2707. Min Act: -0.1700
Data Index: 4331476 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19