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

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

Neuron 3751 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0211. Min Act: -0.0001

Data Index: 751578 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0210. Min Act: -0.0001

Data Index: 834439 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0001

Data Index: 588330 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1458309 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0202. Min Act: -0.0001

Data Index: 1333783 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0189. Min Act: -0.0001

Data Index: 1623723 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1292941 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0183. Min Act: -0.0001

Data Index: 604200 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1533447 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0184. Min Act: -0.0001

Data Index: 601395 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0167. Min Act: -0.0001

Data Index: 612186 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0172. Min Act: -0.0001

Data Index: 993872 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0165. Min Act: -0.0001

Data Index: 310272 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0156. Min Act: -0.0001

Data Index: 793249 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1146977 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1378731 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1423589 (Python Code)

Max Activating Token Index: 83

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0155. Min Act: -0.0001

Data Index: 495089 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0157. Min Act: -0.0001

Data Index: 928895 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0164. Min Act: -0.0001

Data Index: 819728 (C4 (Web Text))

Max Activating Token Index: 804