Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1846 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1074155 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2572. Min Act: -0.0001

Data Index: 395230 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2286. Min Act: -0.0001

Data Index: 845456 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2357. Min Act: -0.0001

Data Index: 2143 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2335. Min Act: -0.0001

Data Index: 453757 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2406. Min Act: -0.0001

Data Index: 1088431 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2204. Min Act: -0.0001

Data Index: 902092 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2271. Min Act: -0.0001

Data Index: 1022661 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2337. Min Act: -0.0001

Data Index: 1107774 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2187. Min Act: -0.0001

Data Index: 791779 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2490. Min Act: -0.0001

Data Index: 128073 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2068. Min Act: -0.0001

Data Index: 687959 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2056. Min Act: -0.0001

Data Index: 345224 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2222. Min Act: -0.0001

Data Index: 363562 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2131. Min Act: -0.0001

Data Index: 1312951 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2118. Min Act: -0.0001

Data Index: 257774 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2194. Min Act: -0.0001

Data Index: 753618 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2198. Min Act: -0.0001

Data Index: 858970 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2089. Min Act: -0.0001

Data Index: 536103 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.2687. Min Range: -0.2687

Max Act: 0.2021. Min Act: -0.0001

Data Index: 570505 (C4 (Web Text))

Max Activating Token Index: 62