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

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

Neuron 806 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1082989 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2278. Min Act: -0.0002

Data Index: 241347 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1130340 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2179. Min Act: -0.0001

Data Index: 1212520 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2171. Min Act: -0.0002

Data Index: 486476 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1169474 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2139. Min Act: -0.0001

Data Index: 235643 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2261. Min Act: -0.0002

Data Index: 511627 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1099400 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2021. Min Act: -0.0002

Data Index: 418730 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2068. Min Act: -0.0001

Data Index: 931980 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2300. Min Act: -0.0001

Data Index: 446524 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2212. Min Act: -0.0002

Data Index: 1339514 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2055. Min Act: -0.0001

Data Index: 403028 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2174. Min Act: -0.0001

Data Index: 414281 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2033. Min Act: -0.0002

Data Index: 140905 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2020. Min Act: -0.0001

Data Index: 294875 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2046. Min Act: -0.0001

Data Index: 1017287 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1951. Min Act: -0.0001

Data Index: 50223 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1324780 (C4 (Web Text))

Max Activating Token Index: 566