Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2352 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.4363. Min Act: -0.1700
Data Index: 2970860 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.3738. Min Act: -0.1700
Data Index: 7095345 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.3425. Min Act: -0.1700
Data Index: 6492594 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.3113. Min Act: -0.1700
Data Index: 2141787 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.3113. Min Act: -0.1700
Data Index: 8560432 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.2488. Min Act: -0.1700
Data Index: 1991857 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.2488. Min Act: -0.1700
Data Index: 6655910 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.2175. Min Act: -0.1700
Data Index: 6046766 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.2488. Min Act: -0.1700
Data Index: 7487684 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.2175. Min Act: -0.1700
Data Index: 813438 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.2175. Min Act: -0.1700
Data Index: 4046073 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.2175. Min Act: -0.1700
Data Index: 6607998 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.1863. Min Act: -0.1700
Data Index: 8689085 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.1863. Min Act: -0.1700
Data Index: 8637960 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.1863. Min Act: -0.1700
Data Index: 6376473 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.1863. Min Act: -0.1700
Data Index: 4046072 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.1863. Min Act: -0.1700
Data Index: 1942759 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.1550. Min Act: -0.1700
Data Index: 6678428 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.1237. Min Act: -0.1700
Data Index: 4505944 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4363. Min Range: -4.4363
Max Act: 4.1550. Min Act: -0.1700
Data Index: 7755501 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19