Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7362. Min Range: -7.7362
Max Act: 7.7362. Min Act: -0.1700
Data Index: 812747 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.5799. Min Act: -0.1700
Data Index: 2001514 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.5487. Min Act: -0.1700
Data Index: 2091687 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.5487. Min Act: -0.1700
Data Index: 3165366 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.5174. Min Act: -0.1700
Data Index: 6728107 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.4862. Min Act: -0.1700
Data Index: 1169609 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.4237. Min Act: -0.1700
Data Index: 4124814 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.4237. Min Act: -0.1700
Data Index: 1957332 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.3924. Min Act: -0.1700
Data Index: 8525675 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.3612. Min Act: -0.1700
Data Index: 8811379 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.3924. Min Act: -0.1700
Data Index: 4342454 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.2674. Min Act: -0.1700
Data Index: 6561428 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.2674. Min Act: -0.1700
Data Index: 2006234 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.2362. Min Act: -0.1700
Data Index: 2383680 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.2049. Min Act: -0.1700
Data Index: 5999706 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.1737. Min Act: -0.1700
Data Index: 3655631 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.1424. Min Act: -0.1700
Data Index: 2899093 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.1737. Min Act: -0.1700
Data Index: 1582166 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.1424. Min Act: -0.1700
Data Index: 4627648 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7362. Min Range: -7.7362
Max Act: 6.1424. Min Act: -0.1700
Data Index: 8614354 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19