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

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

Neuron 3857 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: 1.7213. Min Range: -1.7213

Max Act: 1.7213. Min Act: -0.0000

Data Index: 84578 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.4836. Min Act: -0.0000

Data Index: 173751 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.3943. Min Act: -0.0000

Data Index: 30372 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.4177. Min Act: -0.0000

Data Index: 344558 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1522283 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1006645 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.3332. Min Act: -0.0000

Data Index: 136616 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.3102. Min Act: -0.0000

Data Index: 1063443 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1101881 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1796. Min Act: -0.0000

Data Index: 159130 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.2440. Min Act: -0.0000

Data Index: 186988 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1153. Min Act: -0.0000

Data Index: 2883 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.2297. Min Act: -0.0000

Data Index: 468066 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1698. Min Act: -0.0000

Data Index: 530072 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1043460 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1450. Min Act: -0.0000

Data Index: 605288 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1193. Min Act: -0.0000

Data Index: 90008 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1117. Min Act: -0.0000

Data Index: 675786 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1456. Min Act: -0.0000

Data Index: 618905 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.0766. Min Act: -0.0000

Data Index: 419848 (C4 (Web Text))

Max Activating Token Index: 363