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

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

Neuron 496 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1363437 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1591958 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1230516 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1518220 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1228. Min Act: -0.0002

Data Index: 168313 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1258. Min Act: -0.0002

Data Index: 927981 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1582255 (Python Code)

Max Activating Token Index: 574

Text #7

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1249139 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1615400 (Python Code)

Max Activating Token Index: 958

Text #9

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1160. Min Act: -0.0001

Data Index: 743144 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1455105 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1391729 (Python Code)

Max Activating Token Index: 825

Text #12

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1371590 (Python Code)

Max Activating Token Index: 900

Text #13

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1483028 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1523599 (Python Code)

Max Activating Token Index: 924

Text #15

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1458718 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1208. Min Act: -0.0002

Data Index: 1336701 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1046229 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1466318 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1277762 (C4 (Web Text))

Max Activating Token Index: 888