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

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

Neuron 3170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.2119. Min Act: -0.0000

Data Index: 830707 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1584. Min Act: -0.0000

Data Index: 385327 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1486. Min Act: -0.0000

Data Index: 988635 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1570. Min Act: -0.0000

Data Index: 245536 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1454. Min Act: -0.0000

Data Index: 930337 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1345. Min Act: -0.0000

Data Index: 895183 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1149964 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1241. Min Act: -0.0000

Data Index: 64003 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1209. Min Act: -0.0000

Data Index: 851970 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1247. Min Act: -0.0001

Data Index: 871361 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1210. Min Act: -0.0001

Data Index: 59681 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1206. Min Act: -0.0001

Data Index: 567093 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1332. Min Act: -0.0000

Data Index: 29819 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1177. Min Act: -0.0000

Data Index: 192874 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1171. Min Act: -0.0001

Data Index: 576113 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1063. Min Act: -0.0001

Data Index: 857882 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1165. Min Act: -0.0001

Data Index: 352569 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1159. Min Act: -0.0000

Data Index: 925421 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.1070. Min Act: -0.0000

Data Index: 828644 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.2119. Min Range: -0.2119

Max Act: 0.0994. Min Act: -0.0001

Data Index: 914738 (C4 (Web Text))

Max Activating Token Index: 838