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

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

Neuron 575 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1722. Min Act: -0.0000

Data Index: 701096 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1490. Min Act: -0.0000

Data Index: 5233 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1529. Min Act: -0.0001

Data Index: 355411 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1381920 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1350. Min Act: -0.0000

Data Index: 392128 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1241. Min Act: -0.0001

Data Index: 372251 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1232. Min Act: -0.0000

Data Index: 382726 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1584991 (Python Code)

Max Activating Token Index: 451

Text #8

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1135. Min Act: -0.0000

Data Index: 292656 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1250. Min Act: -0.0000

Data Index: 680447 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1116. Min Act: -0.0000

Data Index: 247016 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1092722 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1297621 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1164285 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1084110 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1415778 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1127. Min Act: -0.0000

Data Index: 655145 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1119. Min Act: -0.0000

Data Index: 661376 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1353392 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1334018 (C4 (Web Text))

Max Activating Token Index: 162