Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.6397. Min Act: -0.1700
Data Index: 2561369 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.5147. Min Act: -0.1700
Data Index: 220673 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.3897. Min Act: -0.1700
Data Index: 7761768 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.4522. Min Act: -0.1700
Data Index: 8130859 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2647. Min Act: -0.1700
Data Index: 5703380 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2647. Min Act: -0.1700
Data Index: 382827 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2647. Min Act: -0.1700
Data Index: 5994970 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.3272. Min Act: -0.1700
Data Index: 4952285 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2647. Min Act: -0.1700
Data Index: 4209381 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2022. Min Act: -0.1700
Data Index: 7610926 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.2022. Min Act: -0.1700
Data Index: 8595504 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 4175632 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 4389172 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 3815326 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 1246730 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 6548269 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 8699344 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.0772. Min Act: -0.1700
Data Index: 1004810 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.0772. Min Act: -0.1700
Data Index: 1747189 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6397. Min Range: -8.6397
Max Act: 8.0772. Min Act: -0.1700
Data Index: 930176 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19