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

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

Neuron 1387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.2001. Min Act: -0.0000

Data Index: 814839 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.2268. Min Act: -0.0000

Data Index: 710747 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1532. Min Act: -0.0000

Data Index: 937056 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.0667. Min Act: -0.0001

Data Index: 444131 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.0939. Min Act: -0.0000

Data Index: 186882 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1216. Min Act: -0.0001

Data Index: 73820 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.0787. Min Act: -0.0000

Data Index: 146481 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1358130 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1216273 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9970. Min Act: -0.0001

Data Index: 796456 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.0170. Min Act: -0.0001

Data Index: 1004020 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9627. Min Act: -0.0000

Data Index: 430381 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9831. Min Act: -0.0001

Data Index: 173409 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9226. Min Act: -0.0001

Data Index: 213860 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9181. Min Act: -0.0001

Data Index: 146067 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.0041. Min Act: -0.0001

Data Index: 583700 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9005. Min Act: -0.0001

Data Index: 1307561 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9537. Min Act: -0.0000

Data Index: 866571 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9215. Min Act: -0.0000

Data Index: 956184 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9488. Min Act: -0.0000

Data Index: 7608 (C4 (Web Text))

Max Activating Token Index: 477