Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 268 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0000

Data Index: 806854 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1106867 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1337. Min Act: -0.0000

Data Index: 559246 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1325. Min Act: -0.0000

Data Index: 422717 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1303522 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1455364 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1181. Min Act: -0.0000

Data Index: 375595 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1635789 (Python Code)

Max Activating Token Index: 1020

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1176. Min Act: -0.0000

Data Index: 140504 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1076. Min Act: -0.0000

Data Index: 882744 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1159. Min Act: -0.0000

Data Index: 92583 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1073. Min Act: -0.0000

Data Index: 761237 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1072. Min Act: -0.0000

Data Index: 181220 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1091. Min Act: -0.0000

Data Index: 238545 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1134. Min Act: -0.0000

Data Index: 707418 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1032. Min Act: -0.0000

Data Index: 952468 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1059. Min Act: -0.0000

Data Index: 138285 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1027. Min Act: -0.0000

Data Index: 426073 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1116. Min Act: -0.0000

Data Index: 156027 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1548259 (Python Code)

Max Activating Token Index: 926