Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 356 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.7760. Min Act: -0.1700
Data Index: 3063146 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.6510. Min Act: -0.1700
Data Index: 6289774 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.6198. Min Act: -0.1700
Data Index: 7824986 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.5573. Min Act: -0.1700
Data Index: 2958946 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.5260. Min Act: -0.1700
Data Index: 5611395 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.5260. Min Act: -0.1700
Data Index: 1550356 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4948. Min Act: -0.1700
Data Index: 6485678 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4948. Min Act: -0.1700
Data Index: 1093885 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4948. Min Act: -0.1700
Data Index: 7303830 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4948. Min Act: -0.1700
Data Index: 7521582 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4948. Min Act: -0.1700
Data Index: 4100756 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4635. Min Act: -0.1700
Data Index: 3239996 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4948. Min Act: -0.1700
Data Index: 8730360 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4635. Min Act: -0.1700
Data Index: 308835 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4323. Min Act: -0.1700
Data Index: 3947035 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4323. Min Act: -0.1700
Data Index: 2874940 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4323. Min Act: -0.1700
Data Index: 201021 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4323. Min Act: -0.1700
Data Index: 615293 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4323. Min Act: -0.1700
Data Index: 5592144 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7760. Min Range: -4.7760
Max Act: 4.4323. Min Act: -0.1700
Data Index: 1220315 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19