Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0440. Min Range: -7.0440
Max Act: 7.0440. Min Act: -0.1700
Data Index: 545914 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0440. Min Range: -7.0440
Max Act: 7.0440. Min Act: -0.1700
Data Index: 3516671 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0440. Min Range: -7.0440
Max Act: 7.0127. Min Act: -0.1700
Data Index: 4298787 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.9815. Min Act: -0.1700
Data Index: 2928477 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.9190. Min Act: -0.1700
Data Index: 5860140 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.9190. Min Act: -0.1700
Data Index: 5723820 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.9190. Min Act: -0.1700
Data Index: 4543793 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.9502. Min Act: -0.1700
Data Index: 5771905 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.8877. Min Act: -0.1700
Data Index: 1069671 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.8877. Min Act: -0.1700
Data Index: 5046363 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.8252. Min Act: -0.1700
Data Index: 462293 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7940. Min Act: -0.1700
Data Index: 5631171 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7627. Min Act: -0.1700
Data Index: 6667169 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7315. Min Act: -0.1700
Data Index: 3065986 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7627. Min Act: -0.1700
Data Index: 8145076 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7627. Min Act: -0.1700
Data Index: 7634968 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7002. Min Act: -0.1700
Data Index: 1731193 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7002. Min Act: -0.1700
Data Index: 2056607 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7002. Min Act: -0.1700
Data Index: 5709508 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0440. Min Range: -7.0440
Max Act: 6.7002. Min Act: -0.1700
Data Index: 6285195 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19