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

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

Neuron 2012 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1863. Min Act: -0.0000

Data Index: 603410 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1670. Min Act: -0.0000

Data Index: 377026 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1267305 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1327. Min Act: -0.0000

Data Index: 301921 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1352. Min Act: -0.0000

Data Index: 815011 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1397. Min Act: -0.0000

Data Index: 664483 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1280. Min Act: -0.0000

Data Index: 604307 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1257. Min Act: -0.0000

Data Index: 189514 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1134087 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1216. Min Act: -0.0000

Data Index: 588048 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1180595 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1116. Min Act: -0.0000

Data Index: 18167 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1152. Min Act: -0.0000

Data Index: 969273 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1273. Min Act: -0.0000

Data Index: 514478 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1190. Min Act: -0.0000

Data Index: 205973 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1064606 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1154860 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1267589 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1162. Min Act: -0.0000

Data Index: 237457 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1033. Min Act: -0.0000

Data Index: 719262 (C4 (Web Text))

Max Activating Token Index: 1009