Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.7230. Min Act: -0.1700
Data Index: 7378854 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.7230. Min Act: -0.1700
Data Index: 1391259 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.6917. Min Act: -0.1700
Data Index: 1526597 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5980. Min Act: -0.1700
Data Index: 201494 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.6292. Min Act: -0.1700
Data Index: 61552 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.6292. Min Act: -0.1700
Data Index: 4875860 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5980. Min Act: -0.1700
Data Index: 7893409 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5980. Min Act: -0.1700
Data Index: 3287497 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5355. Min Act: -0.1700
Data Index: 3427417 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5042. Min Act: -0.1700
Data Index: 5157432 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5355. Min Act: -0.1700
Data Index: 6587947 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5355. Min Act: -0.1700
Data Index: 1802794 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5042. Min Act: -0.1700
Data Index: 825725 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5042. Min Act: -0.1700
Data Index: 804054 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.4730. Min Act: -0.1700
Data Index: 8359176 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.5355. Min Act: -0.1700
Data Index: 3404179 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.4417. Min Act: -0.1700
Data Index: 415833 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.4730. Min Act: -0.1700
Data Index: 3348571 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.4730. Min Act: -0.1700
Data Index: 1337343 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7230. Min Range: -5.7230
Max Act: 5.4105. Min Act: -0.1700
Data Index: 5822544 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19