Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1955 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1749. Min Act: -0.0003

Data Index: 1280844 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1651. Min Act: -0.0003

Data Index: 951336 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1622. Min Act: -0.0003

Data Index: 590354 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1595. Min Act: -0.0003

Data Index: 1084370 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1501. Min Act: -0.0003

Data Index: 140448 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1458. Min Act: -0.0003

Data Index: 1211163 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1381. Min Act: -0.0003

Data Index: 707042 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1462. Min Act: -0.0003

Data Index: 895726 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1471. Min Act: -0.0003

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1337. Min Act: -0.0003

Data Index: 1527378 (Python Code)

Max Activating Token Index: 919

Text #10

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1283. Min Act: -0.0003

Data Index: 895077 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1332. Min Act: -0.0003

Data Index: 643849 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1384. Min Act: -0.0003

Data Index: 189355 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1302. Min Act: -0.0003

Data Index: 36403 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1335. Min Act: -0.0003

Data Index: 1482269 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1270. Min Act: -0.0003

Data Index: 912526 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1208. Min Act: -0.0003

Data Index: 1089396 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1221. Min Act: -0.0003

Data Index: 118540 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1236. Min Act: -0.0003

Data Index: 1228038 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1507054 (Python Code)

Max Activating Token Index: 419