Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4107 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7715. Min Range: -9.7715
Max Act: 9.7715. Min Act: -0.1700
Data Index: 4694607 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7715. Min Range: -9.7715
Max Act: 9.4590. Min Act: -0.1700
Data Index: 231853 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7715. Min Range: -9.7715
Max Act: 9.2090. Min Act: -0.1700
Data Index: 3839796 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.8965. Min Act: -0.1700
Data Index: 183968 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.8965. Min Act: -0.1700
Data Index: 1860614 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.8965. Min Act: -0.1700
Data Index: 2615303 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.9590. Min Act: -0.1700
Data Index: 8414123 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.8340. Min Act: -0.1700
Data Index: 4228279 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.8340. Min Act: -0.1700
Data Index: 3688490 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.8340. Min Act: -0.1700
Data Index: 6928072 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7715. Min Act: -0.1700
Data Index: 1158031 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7090. Min Act: -0.1700
Data Index: 8373207 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7090. Min Act: -0.1700
Data Index: 4757950 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7090. Min Act: -0.1700
Data Index: 6543613 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7090. Min Act: -0.1700
Data Index: 8433233 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7090. Min Act: -0.1700
Data Index: 1698885 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7090. Min Act: -0.1700
Data Index: 6245016 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7090. Min Act: -0.1700
Data Index: 1306923 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.7090. Min Act: -0.1700
Data Index: 460813 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7715. Min Range: -9.7715
Max Act: 8.6465. Min Act: -0.1700
Data Index: 2620102 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19