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

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

Neuron 3148 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1675. Min Range: -2.1675

Max Act: 2.1675. Min Act: -0.0000

Data Index: 433968 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.6886. Min Act: -0.0000

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1246757 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.6079. Min Act: -0.0000

Data Index: 710826 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.5582. Min Act: -0.0000

Data Index: 555864 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.3655. Min Act: -0.0000

Data Index: 883211 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.4775. Min Act: -0.0000

Data Index: 291695 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.2241. Min Act: -0.0000

Data Index: 1343350 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.1519. Min Act: -0.0000

Data Index: 658647 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.1214. Min Act: -0.0000

Data Index: 825106 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.1266. Min Act: -0.0000

Data Index: 533984 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.1239. Min Act: -0.0000

Data Index: 45151 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.1097. Min Act: -0.0000

Data Index: 191221 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.0978. Min Act: -0.0000

Data Index: 830867 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.0928. Min Act: -0.0000

Data Index: 177393 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.0444. Min Act: -0.0000

Data Index: 471874 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.0390. Min Act: -0.0000

Data Index: 670105 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 2.1675. Min Range: -2.1675

Max Act: 0.9885. Min Act: -0.0000

Data Index: 503290 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.0310. Min Act: -0.0000

Data Index: 106009 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 2.1675. Min Range: -2.1675

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1061192 (C4 (Web Text))

Max Activating Token Index: 328