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

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

Neuron 281 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1029301 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1247382 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1152066 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3446. Min Act: -0.0000

Data Index: 135974 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1216029 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2611. Min Act: -0.0000

Data Index: 313962 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2352. Min Act: -0.0000

Data Index: 277111 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1030140 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2185. Min Act: -0.0000

Data Index: 10268 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2208. Min Act: -0.0000

Data Index: 646326 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2387. Min Act: -0.0000

Data Index: 325739 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2162. Min Act: -0.0000

Data Index: 713220 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1606827 (Python Code)

Max Activating Token Index: 289

Text #13

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2202. Min Act: -0.0000

Data Index: 259983 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1638135 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2077. Min Act: -0.0000

Data Index: 891630 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2109. Min Act: -0.0000

Data Index: 334824 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1434434 (Python Code)

Max Activating Token Index: 402

Text #18

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1651691 (Python Code)

Max Activating Token Index: 608

Text #19

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2014. Min Act: -0.0000

Data Index: 854830 (C4 (Web Text))

Max Activating Token Index: 160