Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.8374. Min Act: -0.1700
Data Index: 5162496 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.6499. Min Act: -0.1700
Data Index: 1297546 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.5874. Min Act: -0.1700
Data Index: 2091819 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.5249. Min Act: -0.1700
Data Index: 3337551 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.4937. Min Act: -0.1700
Data Index: 6948299 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.4312. Min Act: -0.1700
Data Index: 8073006 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3999. Min Act: -0.1700
Data Index: 4280367 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3999. Min Act: -0.1700
Data Index: 5007910 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3374. Min Act: -0.1700
Data Index: 8772630 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3062. Min Act: -0.1700
Data Index: 7936936 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.2749. Min Act: -0.1700
Data Index: 8155266 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.2437. Min Act: -0.1700
Data Index: 3337549 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.2124. Min Act: -0.1700
Data Index: 8233584 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.1812. Min Act: -0.1700
Data Index: 8214897 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.1812. Min Act: -0.1700
Data Index: 4475534 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.1499. Min Act: -0.1700
Data Index: 1136553 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.1499. Min Act: -0.1700
Data Index: 6848534 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.1812. Min Act: -0.1700
Data Index: 1621879 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.1187. Min Act: -0.1700
Data Index: 196926 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.1187. Min Act: -0.1700
Data Index: 2520309 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19