Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2901 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1400. Min Act: -0.0001

Data Index: 578543 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1448. Min Act: -0.0001

Data Index: 203974 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1286763 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1290. Min Act: -0.0001

Data Index: 303569 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1228. Min Act: -0.0001

Data Index: 900732 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1266. Min Act: -0.0001

Data Index: 786525 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1334175 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1207763 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1208803 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1048. Min Act: -0.0001

Data Index: 433046 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1199213 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1117. Min Act: -0.0001

Data Index: 463011 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1518893 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1178294 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1071. Min Act: -0.0001

Data Index: 233602 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1220269 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1144607 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1055. Min Act: -0.0001

Data Index: 949147 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1086. Min Act: -0.0001

Data Index: 317757 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1083. Min Act: -0.0001

Data Index: 456760 (C4 (Web Text))

Max Activating Token Index: 423