Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 906 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8053. Min Range: -7.8053
Max Act: 7.8053. Min Act: -0.1700
Data Index: 4589024 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8053. Min Range: -7.8053
Max Act: 7.4303. Min Act: -0.1700
Data Index: 8589107 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8053. Min Range: -7.8053
Max Act: 7.2115. Min Act: -0.1700
Data Index: 1409654 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8053. Min Range: -7.8053
Max Act: 7.2115. Min Act: -0.1700
Data Index: 6140144 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8053. Min Range: -7.8053
Max Act: 7.1490. Min Act: -0.1700
Data Index: 2591225 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8053. Min Range: -7.8053
Max Act: 7.0553. Min Act: -0.1700
Data Index: 3607326 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8053. Min Range: -7.8053
Max Act: 7.0240. Min Act: -0.1700
Data Index: 397153 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.9928. Min Act: -0.1700
Data Index: 4615506 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.9303. Min Act: -0.1700
Data Index: 595670 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.8990. Min Act: -0.1700
Data Index: 613827 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.8678. Min Act: -0.1700
Data Index: 6337015 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.8053. Min Act: -0.1700
Data Index: 1584929 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.8365. Min Act: -0.1700
Data Index: 1532891 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.7740. Min Act: -0.1700
Data Index: 1615263 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.7740. Min Act: -0.1700
Data Index: 3266276 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.7428. Min Act: -0.1700
Data Index: 1660242 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.7740. Min Act: -0.1700
Data Index: 6288940 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.7740. Min Act: -0.1700
Data Index: 5531961 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.7740. Min Act: -0.1700
Data Index: 5682518 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8053. Min Range: -7.8053
Max Act: 6.7428. Min Act: -0.1700
Data Index: 637114 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19