Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.6676. Min Act: -0.1700
Data Index: 2022754 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.6364. Min Act: -0.1700
Data Index: 7912551 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.5739. Min Act: -0.1700
Data Index: 7182631 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.6051. Min Act: -0.1700
Data Index: 6177217 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.5426. Min Act: -0.1700
Data Index: 7798322 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.5114. Min Act: -0.1700
Data Index: 8676716 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4801. Min Act: -0.1700
Data Index: 7514924 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4801. Min Act: -0.1700
Data Index: 7949642 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4801. Min Act: -0.1700
Data Index: 1088952 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4489. Min Act: -0.1700
Data Index: 1945923 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4489. Min Act: -0.1700
Data Index: 8030356 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4176. Min Act: -0.1700
Data Index: 6853494 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4176. Min Act: -0.1700
Data Index: 6161517 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4176. Min Act: -0.1700
Data Index: 722318 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4176. Min Act: -0.1700
Data Index: 3027083 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3864. Min Act: -0.1700
Data Index: 5689014 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3551. Min Act: -0.1700
Data Index: 3844588 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3551. Min Act: -0.1700
Data Index: 3296566 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3864. Min Act: -0.1700
Data Index: 4966919 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3864. Min Act: -0.1700
Data Index: 4019380 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19