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

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

Neuron 5829 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: 2.7213. Min Range: -2.7213

Max Act: 2.7213. Min Act: -0.0000

Data Index: 99923 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.5254. Min Act: -0.0000

Data Index: 1273452 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.3765. Min Act: -0.0000

Data Index: 183584 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.2309. Min Act: -0.0000

Data Index: 1003815 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.3291. Min Act: -0.0000

Data Index: 408107 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.3263. Min Act: -0.0000

Data Index: 1217252 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.0421. Min Act: -0.0000

Data Index: 1138545 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.4845. Min Act: -0.0000

Data Index: 1199095 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.2288. Min Act: -0.0000

Data Index: 1072648 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.3438. Min Act: -0.0000

Data Index: 178798 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.0649. Min Act: -0.0000

Data Index: 886477 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.0512. Min Act: -0.0000

Data Index: 100763 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.1554. Min Act: -0.0000

Data Index: 285383 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1231924 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 2.7213. Min Range: -2.7213

Max Act: 1.9527. Min Act: -0.0000

Data Index: 82694 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 2.7213. Min Range: -2.7213

Max Act: 1.9973. Min Act: -0.0000

Data Index: 170640 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.1342. Min Act: -0.0000

Data Index: 236726 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.1357. Min Act: -0.0000

Data Index: 121977 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.1238. Min Act: -0.0000

Data Index: 90665 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 2.7213. Min Range: -2.7213

Max Act: 2.1912. Min Act: -0.0000

Data Index: 11190 (C4 (Web Text))

Max Activating Token Index: 908