Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3906 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5938. Min Act: -0.0000

Data Index: 1005465 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5363. Min Act: -0.0000

Data Index: 622254 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.4683. Min Act: -0.0000

Data Index: 301854 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.3304. Min Act: -0.0000

Data Index: 670948 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.4116. Min Act: -0.0000

Data Index: 1230752 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.4090. Min Act: 0.0000

Data Index: 1317274 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2642. Min Act: -0.0000

Data Index: 652412 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.3925. Min Act: -0.0000

Data Index: 902965 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2677. Min Act: -0.0000

Data Index: 852517 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.3922. Min Act: -0.0000

Data Index: 1245424 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.3372. Min Act: -0.0000

Data Index: 992226 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.3029. Min Act: -0.0000

Data Index: 650416 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2823. Min Act: -0.0000

Data Index: 136915 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2975. Min Act: -0.0000

Data Index: 463351 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2790. Min Act: -0.0000

Data Index: 381751 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2534. Min Act: -0.0000

Data Index: 748572 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2282. Min Act: -0.0000

Data Index: 917743 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2250. Min Act: -0.0000

Data Index: 393782 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.2196. Min Act: -0.0000

Data Index: 1187515 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.0950. Min Act: -0.0000

Data Index: 954268 (C4 (Web Text))

Max Activating Token Index: 977