Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1399. Min Range: -8.1399
Max Act: 8.1399. Min Act: -0.1700
Data Index: 8671048 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.8899. Min Act: -0.1700
Data Index: 7488345 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.8274. Min Act: -0.1700
Data Index: 1067771 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.7649. Min Act: -0.1700
Data Index: 6575198 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.7024. Min Act: -0.1700
Data Index: 7488397 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.5149. Min Act: -0.1700
Data Index: 5411177 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.4211. Min Act: -0.1700
Data Index: 5355956 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.4211. Min Act: -0.1700
Data Index: 8502571 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.4211. Min Act: -0.1700
Data Index: 5891694 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.3586. Min Act: -0.1700
Data Index: 3247410 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.3899. Min Act: -0.1700
Data Index: 7138756 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.3274. Min Act: -0.1700
Data Index: 4055215 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.3274. Min Act: -0.1700
Data Index: 4104799 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.2961. Min Act: -0.1700
Data Index: 2444341 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.2649. Min Act: -0.1700
Data Index: 7976431 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.2336. Min Act: -0.1700
Data Index: 4847002 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.2649. Min Act: -0.1700
Data Index: 7693729 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.2336. Min Act: -0.1700
Data Index: 3206983 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.2024. Min Act: -0.1700
Data Index: 312245 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1399. Min Range: -8.1399
Max Act: 7.2024. Min Act: -0.1700
Data Index: 2945580 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19