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

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

Neuron 952 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2665. Min Act: -0.0001

Data Index: 518076 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2119. Min Act: -0.0001

Data Index: 252901 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1283276 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2260. Min Act: -0.0001

Data Index: 965324 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2227. Min Act: -0.0001

Data Index: 903252 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2314. Min Act: -0.0001

Data Index: 324205 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2150. Min Act: -0.0001

Data Index: 1199269 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2128. Min Act: -0.0001

Data Index: 128816 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2059. Min Act: -0.0001

Data Index: 1060743 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1274339 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1995. Min Act: -0.0001

Data Index: 1181811 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2211. Min Act: -0.0001

Data Index: 411811 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2001. Min Act: -0.0001

Data Index: 426693 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2020. Min Act: -0.0001

Data Index: 63550 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2019. Min Act: -0.0001

Data Index: 173723 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1871. Min Act: -0.0001

Data Index: 777945 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1134666 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1918. Min Act: -0.0001

Data Index: 887172 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1896. Min Act: -0.0001

Data Index: 384079 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1968. Min Act: -0.0001

Data Index: 816298 (C4 (Web Text))

Max Activating Token Index: 308