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

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

Neuron 2490 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: 0.2908. Min Range: -0.2908

Max Act: 0.2908. Min Act: -0.0001

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2827. Min Act: -0.0001

Data Index: 505463 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2737. Min Act: -0.0001

Data Index: 1308464 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2662. Min Act: -0.0001

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2399. Min Act: -0.0001

Data Index: 533212 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2418. Min Act: -0.0001

Data Index: 421026 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2260. Min Act: -0.0001

Data Index: 1079209 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2416. Min Act: -0.0001

Data Index: 266482 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2259. Min Act: -0.0000

Data Index: 355113 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1136238 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2177. Min Act: -0.0001

Data Index: 84918 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2156. Min Act: -0.0000

Data Index: 148632 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2227. Min Act: -0.0001

Data Index: 141485 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2185. Min Act: -0.0001

Data Index: 209129 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2110. Min Act: -0.0001

Data Index: 182249 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2071. Min Act: -0.0001

Data Index: 153953 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2001. Min Act: -0.0001

Data Index: 294642 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1959. Min Act: -0.0001

Data Index: 176491 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1884. Min Act: -0.0001

Data Index: 55029 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.1942. Min Act: -0.0000

Data Index: 31893 (C4 (Web Text))

Max Activating Token Index: 878