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

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

Neuron 5588 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1208568 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0469. Min Act: -0.0002

Data Index: 486437 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0440. Min Act: -0.0002

Data Index: 889447 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0449. Min Act: -0.0002

Data Index: 219429 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0417. Min Act: -0.0002

Data Index: 339134 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1143409 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0421. Min Act: -0.0002

Data Index: 582939 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0417. Min Act: -0.0002

Data Index: 316436 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0411. Min Act: -0.0002

Data Index: 996281 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0414. Min Act: -0.0002

Data Index: 573308 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0424. Min Act: -0.0002

Data Index: 661195 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1029212 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0428. Min Act: -0.0002

Data Index: 646263 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1235740 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0396. Min Act: -0.0002

Data Index: 669239 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0411. Min Act: -0.0002

Data Index: 961283 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0408. Min Act: -0.0002

Data Index: 236135 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0384. Min Act: -0.0002

Data Index: 698982 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0395. Min Act: -0.0002

Data Index: 210915 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0393. Min Act: -0.0002

Data Index: 524203 (C4 (Web Text))

Max Activating Token Index: 307