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

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

Neuron 1238 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1830. Min Act: -0.0001

Data Index: 659304 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1737. Min Act: -0.0001

Data Index: 461643 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1659. Min Act: -0.0001

Data Index: 250461 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1638. Min Act: -0.0001

Data Index: 185714 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1355. Min Act: -0.0001

Data Index: 574257 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1130905 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1277. Min Act: -0.0001

Data Index: 960321 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1028601 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1233838 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1162668 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1286. Min Act: -0.0001

Data Index: 767088 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1276. Min Act: -0.0001

Data Index: 136359 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1191. Min Act: -0.0001

Data Index: 750379 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1137. Min Act: -0.0001

Data Index: 679456 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1260. Min Act: -0.0001

Data Index: 220737 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1081988 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1169. Min Act: -0.0001

Data Index: 573709 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1254. Min Act: -0.0001

Data Index: 980698 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1254590 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1108. Min Act: -0.0001

Data Index: 34809 (C4 (Web Text))

Max Activating Token Index: 858