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

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

Neuron 5206 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1966. Min Act: -0.0001

Data Index: 335144 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1769. Min Act: -0.0001

Data Index: 717508 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1298. Min Act: -0.0001

Data Index: 265233 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1382. Min Act: -0.0001

Data Index: 829438 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1507. Min Act: -0.0001

Data Index: 608281 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1600. Min Act: -0.0001

Data Index: 108775 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1452. Min Act: -0.0001

Data Index: 332632 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1489. Min Act: -0.0001

Data Index: 390190 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1339304 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1338. Min Act: -0.0002

Data Index: 94075 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1323121 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1145513 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1367. Min Act: -0.0001

Data Index: 233266 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1171. Min Act: -0.0001

Data Index: 769242 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1010. Min Act: -0.0001

Data Index: 286073 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1294. Min Act: -0.0001

Data Index: 353064 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1203268 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1329. Min Act: -0.0001

Data Index: 443508 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1221. Min Act: -0.0001

Data Index: 462045 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1356. Min Act: -0.0001

Data Index: 165091 (C4 (Web Text))

Max Activating Token Index: 154