Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3491. Min Range: -6.3491
Max Act: 6.3491. Min Act: -0.1700
Data Index: 2672228 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3491. Min Range: -6.3491
Max Act: 6.1928. Min Act: -0.1700
Data Index: 897613 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3491. Min Range: -6.3491
Max Act: 6.1303. Min Act: -0.1700
Data Index: 7707678 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3491. Min Range: -6.3491
Max Act: 6.0366. Min Act: -0.1700
Data Index: 4339309 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.9741. Min Act: -0.1700
Data Index: 6923826 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.9116. Min Act: -0.1700
Data Index: 3194987 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.7553. Min Act: -0.1700
Data Index: 7037574 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.7866. Min Act: -0.1700
Data Index: 1202011 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.7866. Min Act: -0.1700
Data Index: 5017359 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.7866. Min Act: -0.1700
Data Index: 316378 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.7553. Min Act: -0.1700
Data Index: 4540639 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.7241. Min Act: -0.1700
Data Index: 6439826 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.7241. Min Act: -0.1700
Data Index: 585240 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.6928. Min Act: -0.1700
Data Index: 3946409 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.6616. Min Act: -0.1700
Data Index: 8475961 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.6616. Min Act: -0.1700
Data Index: 2621771 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.6616. Min Act: -0.1700
Data Index: 6730281 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.6616. Min Act: -0.1700
Data Index: 8737827 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.6616. Min Act: -0.1700
Data Index: 911110 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3491. Min Range: -6.3491
Max Act: 5.6303. Min Act: -0.1700
Data Index: 1076714 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19