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

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

Neuron 1528 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1214. Min Range: -1.1214

Max Act: 1.1140. Min Act: -0.0000

Data Index: 933559 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 1.1214. Min Range: -1.1214

Max Act: 1.1214. Min Act: -0.0000

Data Index: 627200 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9619. Min Act: -0.0000

Data Index: 253395 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1587489 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.8423. Min Act: -0.0000

Data Index: 96672 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1462923 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.8770. Min Act: -0.0000

Data Index: 448841 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.8444. Min Act: -0.0000

Data Index: 238721 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1128853 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1405908 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1287074 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.7338. Min Act: -0.0000

Data Index: 55021 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1388581 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.6587. Min Act: -0.0000

Data Index: 951260 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.6638. Min Act: -0.0000

Data Index: 99113 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1557007 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.6889. Min Act: -0.0000

Data Index: 279276 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1545272 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.6672. Min Act: -0.0000

Data Index: 310517 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1010250 (C4 (Web Text))

Max Activating Token Index: 200