Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2327 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2924. Min Act: -0.0003

Data Index: 483819 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2604. Min Act: -0.0003

Data Index: 458723 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2370. Min Act: -0.0003

Data Index: 147456 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2352. Min Act: -0.0003

Data Index: 1200723 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2426. Min Act: -0.0003

Data Index: 1261441 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2186. Min Act: -0.0003

Data Index: 396794 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2252. Min Act: -0.0003

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2326. Min Act: -0.0003

Data Index: 463897 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2415. Min Act: -0.0003

Data Index: 597851 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2409. Min Act: -0.0003

Data Index: 618580 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2387. Min Act: -0.0003

Data Index: 808656 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2298. Min Act: -0.0003

Data Index: 653839 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2361. Min Act: -0.0003

Data Index: 1072450 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2216. Min Act: -0.0003

Data Index: 714784 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2142. Min Act: -0.0003

Data Index: 613639 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2158. Min Act: -0.0003

Data Index: 615991 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2159. Min Act: -0.0003

Data Index: 905270 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2217. Min Act: -0.0003

Data Index: 1202034 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2162. Min Act: -0.0003

Data Index: 189457 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.2924. Min Range: -0.2924

Max Act: 0.2272. Min Act: -0.0003

Data Index: 342348 (C4 (Web Text))

Max Activating Token Index: 179