Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.4607. Min Act: -0.0001

Data Index: 181557 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.3324. Min Act: -0.0001

Data Index: 1266466 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.1323. Min Act: -0.0001

Data Index: 603341 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.2014. Min Act: -0.0001

Data Index: 500385 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.1935. Min Act: -0.0001

Data Index: 405509 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.1599. Min Act: -0.0001

Data Index: 812153 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.1483. Min Act: -0.0001

Data Index: 523878 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 1.4607. Min Range: -1.4607

Max Act: 0.9969. Min Act: -0.0001

Data Index: 1304434 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.0738. Min Act: -0.0001

Data Index: 142400 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.1212. Min Act: -0.0001

Data Index: 415253 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.4607. Min Range: -1.4607

Max Act: 0.9789. Min Act: -0.0001

Data Index: 695269 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.4607. Min Range: -1.4607

Max Act: 0.9760. Min Act: -0.0001

Data Index: 935108 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.0065. Min Act: -0.0001

Data Index: 105570 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.1313. Min Act: -0.0001

Data Index: 328568 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.0691. Min Act: -0.0000

Data Index: 601341 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 1.4607. Min Range: -1.4607

Max Act: 0.8605. Min Act: -0.0000

Data Index: 420110 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 1.4607. Min Range: -1.4607

Max Act: 0.9691. Min Act: -0.0001

Data Index: 536639 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.4607. Min Range: -1.4607

Max Act: 1.0213. Min Act: -0.0001

Data Index: 1342034 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 1.4607. Min Range: -1.4607

Max Act: 0.9293. Min Act: -0.0001

Data Index: 962004 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.4607. Min Range: -1.4607

Max Act: 0.9270. Min Act: -0.0001

Data Index: 435476 (C4 (Web Text))

Max Activating Token Index: 165