Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3100 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1224114 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7641. Min Act: -0.0001

Data Index: 1480197 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7535. Min Act: -0.0000

Data Index: 731563 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7726. Min Act: -0.0001

Data Index: 1651578 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1136425 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7121. Min Act: -0.0001

Data Index: 1424251 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1419790 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6966. Min Act: -0.0001

Data Index: 1502180 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1365228 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6901. Min Act: -0.0001

Data Index: 1403715 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6381. Min Act: -0.0001

Data Index: 1525504 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1246021 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1228789 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1375752 (Python Code)

Max Activating Token Index: 532

Text #14

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1299060 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6342. Min Act: -0.0000

Data Index: 516887 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5916. Min Act: -0.0001

Data Index: 1519437 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5849. Min Act: -0.0000

Data Index: 105225 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6026. Min Act: -0.0000

Data Index: 737827 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5809. Min Act: -0.0001

Data Index: 1378874 (Python Code)

Max Activating Token Index: 877