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

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

Neuron 4669 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1277541 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1024364 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1130060 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1249894 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1061989 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2711. Min Act: -0.0000

Data Index: 378905 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2542. Min Act: -0.0000

Data Index: 237018 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2619. Min Act: -0.0000

Data Index: 48646 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2290. Min Act: 0.0000

Data Index: 1190818 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2490. Min Act: -0.0000

Data Index: 191718 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2403. Min Act: -0.0000

Data Index: 212720 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2454. Min Act: -0.0000

Data Index: 149167 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2276. Min Act: -0.0000

Data Index: 359026 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2277. Min Act: -0.0000

Data Index: 609315 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2270. Min Act: -0.0000

Data Index: 463130 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2279. Min Act: -0.0000

Data Index: 289496 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2175. Min Act: -0.0000

Data Index: 260804 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1061292 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2167. Min Act: 0.0000

Data Index: 780393 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2392. Min Act: -0.0000

Data Index: 685505 (C4 (Web Text))

Max Activating Token Index: 936