Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4363 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0272. Min Range: -6.0272
Max Act: 6.0272. Min Act: -0.1700
Data Index: 5365834 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.7147. Min Act: -0.1700
Data Index: 4683040 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.7147. Min Act: -0.1700
Data Index: 6289797 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.6835. Min Act: -0.1700
Data Index: 1276430 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.6835. Min Act: -0.1700
Data Index: 7698649 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.6522. Min Act: -0.1700
Data Index: 4219193 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.6210. Min Act: -0.1700
Data Index: 3628924 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5897. Min Act: -0.1700
Data Index: 191221 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5897. Min Act: -0.1700
Data Index: 1942282 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5897. Min Act: -0.1700
Data Index: 8242844 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5585. Min Act: -0.1700
Data Index: 1375523 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5585. Min Act: -0.1700
Data Index: 2052991 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5585. Min Act: -0.1700
Data Index: 5631061 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5272. Min Act: -0.1700
Data Index: 2281935 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5272. Min Act: -0.1700
Data Index: 630076 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.5272. Min Act: -0.1700
Data Index: 5126732 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.4960. Min Act: -0.1700
Data Index: 3839552 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.4647. Min Act: -0.1700
Data Index: 7292273 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.4647. Min Act: -0.1700
Data Index: 2464630 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0272. Min Range: -6.0272
Max Act: 5.4960. Min Act: -0.1700
Data Index: 1739072 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19