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

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

Neuron 5199 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1980. Min Act: -0.0000

Data Index: 128257 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1443. Min Act: -0.0000

Data Index: 571223 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1042501 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1280. Min Act: -0.0000

Data Index: 121317 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1379. Min Act: -0.0000

Data Index: 730244 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1267. Min Act: -0.0000

Data Index: 155743 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1209. Min Act: -0.0000

Data Index: 790753 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1242. Min Act: -0.0000

Data Index: 669387 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1065408 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1186. Min Act: -0.0000

Data Index: 992144 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1058. Min Act: -0.0000

Data Index: 163802 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1179. Min Act: -0.0000

Data Index: 144945 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1136. Min Act: -0.0000

Data Index: 342097 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1264143 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1164. Min Act: -0.0000

Data Index: 233278 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1082. Min Act: -0.0000

Data Index: 168199 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1077864 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1654834 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1124. Min Act: -0.0000

Data Index: 961363 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1119. Min Act: -0.0000

Data Index: 91116 (C4 (Web Text))

Max Activating Token Index: 506