Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2895 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.2867. Min Act: -0.1700
Data Index: 4980020 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.2867. Min Act: -0.1700
Data Index: 2562432 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.2554. Min Act: -0.1700
Data Index: 864614 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.2554. Min Act: -0.1700
Data Index: 1052824 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.2554. Min Act: -0.1700
Data Index: 4390534 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.2242. Min Act: -0.1700
Data Index: 537236 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.2242. Min Act: -0.1700
Data Index: 7075721 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1929. Min Act: -0.1700
Data Index: 4817228 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1929. Min Act: -0.1700
Data Index: 7817900 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1929. Min Act: -0.1700
Data Index: 5744070 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1617. Min Act: -0.1700
Data Index: 2361566 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1617. Min Act: -0.1700
Data Index: 2410880 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1617. Min Act: -0.1700
Data Index: 521169 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1617. Min Act: -0.1700
Data Index: 1031732 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1304. Min Act: -0.1700
Data Index: 4587098 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.1304. Min Act: -0.1700
Data Index: 6497226 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.0679. Min Act: -0.1700
Data Index: 3061904 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.0992. Min Act: -0.1700
Data Index: 4650314 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.0992. Min Act: -0.1700
Data Index: 1709623 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2867. Min Range: -4.2867
Max Act: 4.0992. Min Act: -0.1700
Data Index: 6331744 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19