Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3675. Min Range: -6.3675
Max Act: 6.3675. Min Act: -0.1700
Data Index: 5881112 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3675. Min Range: -6.3675
Max Act: 6.1488. Min Act: -0.1700
Data Index: 6371308 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3675. Min Range: -6.3675
Max Act: 6.0863. Min Act: -0.1700
Data Index: 8661591 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3675. Min Range: -6.3675
Max Act: 6.0238. Min Act: -0.1700
Data Index: 3050642 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.9925. Min Act: -0.1700
Data Index: 6527833 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.9300. Min Act: -0.1700
Data Index: 7089601 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.9613. Min Act: -0.1700
Data Index: 1308674 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.8988. Min Act: -0.1700
Data Index: 447045 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.9300. Min Act: -0.1700
Data Index: 3454575 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.9300. Min Act: -0.1700
Data Index: 5812927 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.8363. Min Act: -0.1700
Data Index: 4554169 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.8050. Min Act: -0.1700
Data Index: 6838425 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.7738. Min Act: -0.1700
Data Index: 8706943 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.7738. Min Act: -0.1700
Data Index: 4191571 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.7738. Min Act: -0.1700
Data Index: 7066544 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.7425. Min Act: -0.1700
Data Index: 2643853 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.7113. Min Act: -0.1700
Data Index: 4838203 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.7113. Min Act: -0.1700
Data Index: 2348365 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.7113. Min Act: -0.1700
Data Index: 6909668 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3675. Min Range: -6.3675
Max Act: 5.6800. Min Act: -0.1700
Data Index: 1164840 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19