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

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

Neuron 2843 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: 0.1959. Min Range: -0.1959

Max Act: 0.1959. Min Act: -0.0002

Data Index: 1402186 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1809. Min Act: -0.0002

Data Index: 1548023 (Python Code)

Max Activating Token Index: 293

Text #2

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1412630 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1478. Min Act: -0.0002

Data Index: 1497297 (Python Code)

Max Activating Token Index: 748

Text #4

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1411. Min Act: -0.0002

Data Index: 1487944 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1388. Min Act: -0.0002

Data Index: 1367970 (Python Code)

Max Activating Token Index: 456

Text #6

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1438. Min Act: -0.0002

Data Index: 1390086 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1608796 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1245. Min Act: -0.0002

Data Index: 1561488 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1552. Min Act: -0.0002

Data Index: 1468954 (Python Code)

Max Activating Token Index: 586

Text #10

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1526513 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1302. Min Act: -0.0002

Data Index: 1598852 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1334. Min Act: -0.0002

Data Index: 1379823 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1625966 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1362. Min Act: -0.0002

Data Index: 1585328 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1654595 (Python Code)

Max Activating Token Index: 247

Text #16

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1497311 (Python Code)

Max Activating Token Index: 184

Text #17

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1580288 (Python Code)

Max Activating Token Index: 578

Text #18

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1529131 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1400587 (Python Code)

Max Activating Token Index: 765