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

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

Neuron 50 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3716. Min Act: -0.0001

Data Index: 1133765 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1240618 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2691. Min Act: -0.0001

Data Index: 1261088 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2585. Min Act: -0.0001

Data Index: 1278958 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2579. Min Act: -0.0001

Data Index: 1301966 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1214875 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2346. Min Act: -0.0001

Data Index: 351734 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2327. Min Act: -0.0001

Data Index: 157683 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2253. Min Act: -0.0001

Data Index: 866887 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2194. Min Act: -0.0001

Data Index: 1038284 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2307. Min Act: -0.0001

Data Index: 602446 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2082. Min Act: -0.0001

Data Index: 1159139 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2077. Min Act: -0.0001

Data Index: 1170981 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1838. Min Act: -0.0001

Data Index: 361500 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2045. Min Act: -0.0001

Data Index: 883243 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2100. Min Act: -0.0001

Data Index: 465210 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2085. Min Act: -0.0001

Data Index: 729538 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2153. Min Act: -0.0001

Data Index: 392893 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2188. Min Act: -0.0001

Data Index: 470856 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1953. Min Act: -0.0001

Data Index: 500469 (C4 (Web Text))

Max Activating Token Index: 915