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

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

Neuron 1776 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: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0001

Data Index: 228807 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1467794 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1604679 (Python Code)

Max Activating Token Index: 430

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1272. Min Act: -0.0002

Data Index: 17298 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1170212 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1477649 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1483804 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1231. Min Act: -0.0002

Data Index: 221031 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1538005 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1537737 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1451991 (Python Code)

Max Activating Token Index: 935

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1394191 (Python Code)

Max Activating Token Index: 653

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1469637 (Python Code)

Max Activating Token Index: 898

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1433072 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1236747 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1110. Min Act: -0.0001

Data Index: 443678 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1371671 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1563882 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1234636 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1134. Min Act: -0.0002

Data Index: 712676 (C4 (Web Text))

Max Activating Token Index: 825