Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2398 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.6252. Min Act: -0.1700
Data Index: 2444947 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.5627. Min Act: -0.1700
Data Index: 8614835 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.5002. Min Act: -0.1700
Data Index: 402842 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.5002. Min Act: -0.1700
Data Index: 7613932 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.4377. Min Act: -0.1700
Data Index: 6885008 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.3127. Min Act: -0.1700
Data Index: 7980140 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.3127. Min Act: -0.1700
Data Index: 33164 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.2502. Min Act: -0.1700
Data Index: 6746773 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.2502. Min Act: -0.1700
Data Index: 5237131 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.2502. Min Act: -0.1700
Data Index: 332665 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.2502. Min Act: -0.1700
Data Index: 5752230 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.1877. Min Act: -0.1700
Data Index: 7713263 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.1252. Min Act: -0.1700
Data Index: 6211360 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.1252. Min Act: -0.1700
Data Index: 4702229 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.0627. Min Act: -0.1700
Data Index: 1594416 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.0627. Min Act: -0.1700
Data Index: 3536325 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.0627. Min Act: -0.1700
Data Index: 8287117 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.0627. Min Act: -0.1700
Data Index: 5718131 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.0627. Min Act: -0.1700
Data Index: 3473205 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6252. Min Range: -10.6252
Max Act: 10.0627. Min Act: -0.1700
Data Index: 2696010 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19