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

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

Neuron 1681 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.2453. Min Act: -0.0005

Data Index: 750764 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.1730. Min Act: -0.0005

Data Index: 679804 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.1334. Min Act: -0.0005

Data Index: 866550 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.1165. Min Act: -0.0005

Data Index: 767054 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.1291. Min Act: -0.0005

Data Index: 252026 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.2231. Min Act: -0.0005

Data Index: 906879 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.1045. Min Act: -0.0005

Data Index: 1271798 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.0571. Min Act: -0.0005

Data Index: 850858 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.0880. Min Act: -0.0005

Data Index: 55128 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.0990. Min Act: -0.0005

Data Index: 934170 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.0033. Min Act: -0.0005

Data Index: 1173298 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.1229. Min Act: -0.0005

Data Index: 1254717 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.2453. Min Range: -1.2453

Max Act: 0.9696. Min Act: -0.0005

Data Index: 995535 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.0201. Min Act: -0.0005

Data Index: 268994 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.1192. Min Act: -0.0005

Data Index: 934079 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 1.2453. Min Range: -1.2453

Max Act: 0.9528. Min Act: -0.0005

Data Index: 974381 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 1.2453. Min Range: -1.2453

Max Act: 1.0078. Min Act: -0.0005

Data Index: 354127 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.2453. Min Range: -1.2453

Max Act: 0.9525. Min Act: -0.0005

Data Index: 929690 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 1.2453. Min Range: -1.2453

Max Act: 0.9729. Min Act: -0.0005

Data Index: 1225765 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 1.2453. Min Range: -1.2453

Max Act: 0.8259. Min Act: -0.0005

Data Index: 1246106 (C4 (Web Text))

Max Activating Token Index: 676