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

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

Neuron 3125 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2276. Min Act: -0.0000

Data Index: 456015 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1352438 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1097306 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1318128 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1468. Min Act: -0.0000

Data Index: 56560 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1468. Min Act: -0.0000

Data Index: 70754 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1283815 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1575. Min Act: -0.0000

Data Index: 660874 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1191311 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1294. Min Act: -0.0000

Data Index: 317801 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1253. Min Act: -0.0000

Data Index: 893516 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1231. Min Act: -0.0000

Data Index: 746296 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1188. Min Act: -0.0000

Data Index: 118053 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1065356 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1654577 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1193. Min Act: -0.0000

Data Index: 703772 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1177. Min Act: -0.0000

Data Index: 248925 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.0901. Min Act: -0.0000

Data Index: 806587 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1148. Min Act: -0.0000

Data Index: 997400 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1099. Min Act: -0.0000

Data Index: 134423 (C4 (Web Text))

Max Activating Token Index: 626