Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3396 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.4883. Min Act: -0.0000

Data Index: 917038 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.5904. Min Act: -0.0000

Data Index: 548155 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.5340. Min Act: -0.0000

Data Index: 305322 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1021139 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.4853. Min Act: -0.0000

Data Index: 598272 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.4599. Min Act: -0.0000

Data Index: 150777 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1628109 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.4607. Min Act: -0.0000

Data Index: 478749 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.4241. Min Act: -0.0000

Data Index: 404935 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.4291. Min Act: -0.0000

Data Index: 561000 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3958. Min Act: -0.0000

Data Index: 98340 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3824. Min Act: 0.0000

Data Index: 69841 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1514526 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3823. Min Act: -0.0000

Data Index: 940443 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1341764 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3635. Min Act: -0.0000

Data Index: 357047 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1574529 (Python Code)

Max Activating Token Index: 888

Text #17

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3639. Min Act: -0.0000

Data Index: 987457 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1539193 (Python Code)

Max Activating Token Index: 668

Text #19

Max Range: 0.5904. Min Range: -0.5904

Max Act: 0.3523. Min Act: -0.0000

Data Index: 804130 (C4 (Web Text))

Max Activating Token Index: 420