Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2368 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.5248. Min Act: -0.1700
Data Index: 2730838 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.5248. Min Act: -0.1700
Data Index: 3369757 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4437. Min Act: -0.1700
Data Index: 5581120 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4437. Min Act: -0.1700
Data Index: 1404535 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4437. Min Act: -0.1700
Data Index: 7610755 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4437. Min Act: -0.1700
Data Index: 6081488 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4437. Min Act: -0.1700
Data Index: 4453349 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4274. Min Act: -0.1700
Data Index: 2487786 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4274. Min Act: -0.1700
Data Index: 8522849 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4437. Min Act: -0.1700
Data Index: 5647902 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4111. Min Act: -0.1700
Data Index: 3655875 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4274. Min Act: -0.1700
Data Index: 8104982 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.3948. Min Act: -0.1700
Data Index: 4130598 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.3948. Min Act: -0.1700
Data Index: 8147373 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4111. Min Act: -0.1700
Data Index: 3643231 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4111. Min Act: -0.1700
Data Index: 2060249 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4111. Min Act: -0.1700
Data Index: 7448985 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.4111. Min Act: -0.1700
Data Index: 450966 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.3948. Min Act: -0.1700
Data Index: 3430163 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5248. Min Range: -2.5248
Max Act: 2.3948. Min Act: -0.1700
Data Index: 5530856 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19