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

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

Neuron 2708 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.4392. Min Act: -0.0001

Data Index: 430983 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.3838. Min Act: -0.0001

Data Index: 1318018 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2944. Min Act: -0.0001

Data Index: 484086 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1870. Min Act: -0.0001

Data Index: 919291 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2239. Min Act: -0.0001

Data Index: 361588 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2171. Min Act: -0.0001

Data Index: 1139828 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1369. Min Act: -0.0001

Data Index: 1210055 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1181. Min Act: -0.0001

Data Index: 873010 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1322. Min Act: -0.0001

Data Index: 241865 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1153. Min Act: -0.0001

Data Index: 926047 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1846. Min Act: -0.0001

Data Index: 91007 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0658. Min Act: -0.0001

Data Index: 819999 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0793. Min Act: -0.0001

Data Index: 995989 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0732. Min Act: -0.0001

Data Index: 101044 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0159. Min Act: -0.0001

Data Index: 122943 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9885. Min Act: -0.0001

Data Index: 52860 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0391. Min Act: -0.0001

Data Index: 227964 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9217. Min Act: -0.0001

Data Index: 819459 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9526. Min Act: -0.0001

Data Index: 287952 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.8624. Min Act: -0.0001

Data Index: 734221 (C4 (Web Text))

Max Activating Token Index: 666