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

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

Neuron 6071 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.3047. Min Act: -0.0000

Data Index: 213373 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.1627. Min Act: -0.0000

Data Index: 677996 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1246691 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.0589. Min Act: -0.0000

Data Index: 283325 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.2042. Min Act: -0.0000

Data Index: 303661 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.1202. Min Act: -0.0000

Data Index: 487752 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 1.3047. Min Range: -1.3047

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1253429 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.0361. Min Act: -0.0000

Data Index: 500769 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.0420. Min Act: -0.0000

Data Index: 896205 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.0373. Min Act: -0.0000

Data Index: 614544 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 1.3047. Min Range: -1.3047

Max Act: 0.9750. Min Act: -0.0000

Data Index: 622345 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.0369. Min Act: -0.0000

Data Index: 416327 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.0306. Min Act: -0.0000

Data Index: 218403 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.0319. Min Act: -0.0000

Data Index: 828320 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 1.3047. Min Range: -1.3047

Max Act: 1.0189. Min Act: -0.0000

Data Index: 336290 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.3047. Min Range: -1.3047

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1105227 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.3047. Min Range: -1.3047

Max Act: 0.9340. Min Act: -0.0000

Data Index: 947592 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 1.3047. Min Range: -1.3047

Max Act: 0.9932. Min Act: -0.0000

Data Index: 161697 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 1.3047. Min Range: -1.3047

Max Act: 0.9912. Min Act: -0.0000

Data Index: 906148 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 1.3047. Min Range: -1.3047

Max Act: 0.9774. Min Act: -0.0000

Data Index: 807712 (C4 (Web Text))

Max Activating Token Index: 265