Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2843 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1713. Min Act: -0.0003

Data Index: 1090815 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1439. Min Act: -0.0003

Data Index: 1292977 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1397. Min Act: -0.0003

Data Index: 616848 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1349. Min Act: -0.0002

Data Index: 843428 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1343. Min Act: -0.0003

Data Index: 886076 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1179. Min Act: -0.0003

Data Index: 1031920 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1225. Min Act: -0.0003

Data Index: 126544 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1146. Min Act: -0.0003

Data Index: 789774 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1140. Min Act: -0.0003

Data Index: 559048 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1138. Min Act: -0.0003

Data Index: 83437 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1129. Min Act: -0.0003

Data Index: 1244563 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1211. Min Act: -0.0003

Data Index: 1087565 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1045. Min Act: -0.0003

Data Index: 666674 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1082. Min Act: -0.0003

Data Index: 828313 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1066. Min Act: -0.0002

Data Index: 9365 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1037. Min Act: -0.0003

Data Index: 1319745 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1116844 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1231265 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1037. Min Act: -0.0003

Data Index: 229236 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1003. Min Act: -0.0003

Data Index: 92366 (C4 (Web Text))

Max Activating Token Index: 353