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

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

Neuron 1435 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.3095. Min Act: -0.0002

Data Index: 424028 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2818. Min Act: -0.0002

Data Index: 573186 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2793. Min Act: -0.0002

Data Index: 383314 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2822. Min Act: -0.0002

Data Index: 310203 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2665. Min Act: -0.0002

Data Index: 788683 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2647. Min Act: -0.0002

Data Index: 1275848 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2563. Min Act: -0.0002

Data Index: 1353477 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2632. Min Act: -0.0002

Data Index: 458823 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2549. Min Act: -0.0002

Data Index: 326144 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2436. Min Act: -0.0002

Data Index: 167448 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2417. Min Act: -0.0002

Data Index: 835911 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2440. Min Act: -0.0002

Data Index: 98626 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2426. Min Act: -0.0002

Data Index: 517247 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2549. Min Act: -0.0002

Data Index: 132912 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2257. Min Act: -0.0002

Data Index: 1297325 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2333. Min Act: -0.0002

Data Index: 1218458 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2241. Min Act: -0.0002

Data Index: 818109 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2341. Min Act: -0.0002

Data Index: 855559 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2222. Min Act: -0.0002

Data Index: 976798 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2222. Min Act: -0.0002

Data Index: 9610 (C4 (Web Text))

Max Activating Token Index: 448