Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2173 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2529. Min Range: -10.2529
Max Act: 10.2529. Min Act: -0.1700
Data Index: 1677382 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2529. Min Range: -10.2529
Max Act: 10.0029. Min Act: -0.1700
Data Index: 5413526 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.9404. Min Act: -0.1700
Data Index: 2870248 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.6904. Min Act: -0.1700
Data Index: 1534775 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.6279. Min Act: -0.1700
Data Index: 7893991 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.6279. Min Act: -0.1700
Data Index: 7268148 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.6279. Min Act: -0.1700
Data Index: 7941477 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.5029. Min Act: -0.1700
Data Index: 6799444 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.5029. Min Act: -0.1700
Data Index: 4050606 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.5654. Min Act: -0.1700
Data Index: 508283 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.4404. Min Act: -0.1700
Data Index: 576412 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.4404. Min Act: -0.1700
Data Index: 6120125 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.4404. Min Act: -0.1700
Data Index: 3190474 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.4404. Min Act: -0.1700
Data Index: 3632646 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.3779. Min Act: -0.1700
Data Index: 450253 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.3154. Min Act: -0.1700
Data Index: 7820187 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.3779. Min Act: -0.1700
Data Index: 1806952 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.3154. Min Act: -0.1700
Data Index: 263462 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.3154. Min Act: -0.1700
Data Index: 55199 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2529. Min Range: -10.2529
Max Act: 9.3154. Min Act: -0.1700
Data Index: 5848775 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19