Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 880 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1510. Min Act: -0.0001

Data Index: 213236 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1569. Min Act: -0.0001

Data Index: 884444 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1616. Min Act: -0.0001

Data Index: 506710 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1513. Min Act: -0.0001

Data Index: 830497 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1349. Min Act: -0.0001

Data Index: 456751 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1294. Min Act: -0.0001

Data Index: 30932 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1269. Min Act: -0.0001

Data Index: 46673 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1222. Min Act: -0.0001

Data Index: 618391 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1234. Min Act: -0.0001

Data Index: 769606 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1235. Min Act: -0.0001

Data Index: 516404 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1289. Min Act: -0.0001

Data Index: 890829 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1278. Min Act: -0.0001

Data Index: 527095 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1183. Min Act: -0.0001

Data Index: 47592 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1240. Min Act: -0.0001

Data Index: 644740 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1188. Min Act: -0.0001

Data Index: 537131 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1226. Min Act: -0.0001

Data Index: 251222 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1129. Min Act: -0.0001

Data Index: 85084 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1171. Min Act: -0.0001

Data Index: 163333 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1164. Min Act: -0.0001

Data Index: 156146 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1096499 (C4 (Web Text))

Max Activating Token Index: 842