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

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

Neuron 3104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1366. Min Act: -0.0001

Data Index: 491667 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1102547 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1278. Min Act: -0.0001

Data Index: 545606 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1131. Min Act: -0.0001

Data Index: 662835 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1201. Min Act: -0.0001

Data Index: 75564 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1111. Min Act: -0.0001

Data Index: 255459 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1154. Min Act: -0.0001

Data Index: 171304 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1065. Min Act: -0.0001

Data Index: 980578 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1090. Min Act: -0.0001

Data Index: 883256 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1018. Min Act: -0.0001

Data Index: 767034 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1046. Min Act: -0.0001

Data Index: 572227 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1258073 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0895. Min Act: -0.0001

Data Index: 200017 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1045. Min Act: -0.0001

Data Index: 738599 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1300940 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1040. Min Act: -0.0001

Data Index: 382496 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1015265 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1097. Min Act: -0.0001

Data Index: 865711 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1161. Min Act: -0.0001

Data Index: 750701 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1056. Min Act: -0.0001

Data Index: 116721 (C4 (Web Text))

Max Activating Token Index: 225