Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 830 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4613. Min Range: -9.4613
Max Act: 9.4613. Min Act: -0.1700
Data Index: 3697839 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4613. Min Range: -9.4613
Max Act: 9.3988. Min Act: -0.1700
Data Index: 8258835 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.8988. Min Act: -0.1700
Data Index: 2263065 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.8363. Min Act: -0.1700
Data Index: 4226676 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.8363. Min Act: -0.1700
Data Index: 8258834 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.7738. Min Act: -0.1700
Data Index: 7686034 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.7113. Min Act: -0.1700
Data Index: 1507290 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.7113. Min Act: -0.1700
Data Index: 130349 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.7113. Min Act: -0.1700
Data Index: 595573 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.7113. Min Act: -0.1700
Data Index: 4307602 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.6488. Min Act: -0.1700
Data Index: 120528 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.6488. Min Act: -0.1700
Data Index: 4296096 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.5863. Min Act: -0.1700
Data Index: 8516449 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.5863. Min Act: -0.1700
Data Index: 7523300 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.5863. Min Act: -0.1700
Data Index: 4540502 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.6488. Min Act: -0.1700
Data Index: 5530863 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.5238. Min Act: -0.1700
Data Index: 4401582 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.5863. Min Act: -0.1700
Data Index: 6215422 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.5238. Min Act: -0.1700
Data Index: 4730440 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4613. Min Range: -9.4613
Max Act: 8.5238. Min Act: -0.1700
Data Index: 8678246 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19