Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5255 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2247. Min Range: -9.2247
Max Act: 9.2247. Min Act: -0.1700
Data Index: 259443 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2247. Min Range: -9.2247
Max Act: 9.0997. Min Act: -0.1700
Data Index: 898209 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2247. Min Range: -9.2247
Max Act: 9.0997. Min Act: -0.1700
Data Index: 8721902 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2247. Min Range: -9.2247
Max Act: 9.0372. Min Act: -0.1700
Data Index: 1480520 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.8497. Min Act: -0.1700
Data Index: 2185175 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.8497. Min Act: -0.1700
Data Index: 5364802 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7872. Min Act: -0.1700
Data Index: 5549803 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7872. Min Act: -0.1700
Data Index: 2829768 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7872. Min Act: -0.1700
Data Index: 3002362 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7872. Min Act: -0.1700
Data Index: 5944622 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7872. Min Act: -0.1700
Data Index: 8555735 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.8497. Min Act: -0.1700
Data Index: 8375322 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7247. Min Act: -0.1700
Data Index: 1689813 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7872. Min Act: -0.1700
Data Index: 2520982 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7247. Min Act: -0.1700
Data Index: 1103437 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.6622. Min Act: -0.1700
Data Index: 6998630 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7247. Min Act: -0.1700
Data Index: 2907407 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7247. Min Act: -0.1700
Data Index: 4272772 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.7247. Min Act: -0.1700
Data Index: 2068916 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2247. Min Range: -9.2247
Max Act: 8.6622. Min Act: -0.1700
Data Index: 5586124 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19