Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1599 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1299. Min Act: -0.0002

Data Index: 573626 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1263. Min Act: -0.0002

Data Index: 619160 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1225. Min Act: -0.0002

Data Index: 936748 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1147. Min Act: -0.0001

Data Index: 76527 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1244. Min Act: -0.0002

Data Index: 941388 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1217. Min Act: -0.0002

Data Index: 482330 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1256401 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1068. Min Act: -0.0002

Data Index: 633148 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1052. Min Act: -0.0002

Data Index: 267539 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1068. Min Act: -0.0002

Data Index: 842767 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0995. Min Act: -0.0002

Data Index: 145886 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1001. Min Act: -0.0002

Data Index: 140172 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1137673 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0922. Min Act: -0.0002

Data Index: 697250 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0927. Min Act: -0.0002

Data Index: 372005 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0970. Min Act: -0.0002

Data Index: 13764 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1011. Min Act: -0.0002

Data Index: 100467 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0979. Min Act: -0.0002

Data Index: 759977 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1107293 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1248730 (C4 (Web Text))

Max Activating Token Index: 663