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

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

Neuron 3730 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.5289. Min Act: -0.0002

Data Index: 385669 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.4813. Min Act: -0.0002

Data Index: 562790 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.2832. Min Act: -0.0002

Data Index: 880859 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1641. Min Act: -0.0002

Data Index: 1224878 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1009. Min Act: -0.0002

Data Index: 351274 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1306. Min Act: -0.0001

Data Index: 735351 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1127. Min Act: -0.0002

Data Index: 119015 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1830. Min Act: -0.0002

Data Index: 173982 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1714. Min Act: -0.0001

Data Index: 404247 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1928. Min Act: -0.0001

Data Index: 154572 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1343. Min Act: -0.0002

Data Index: 133134 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1896. Min Act: -0.0001

Data Index: 768457 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1289. Min Act: -0.0001

Data Index: 22899 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0650. Min Act: -0.0002

Data Index: 1225310 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1580. Min Act: -0.0002

Data Index: 1305753 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1308. Min Act: -0.0001

Data Index: 1525413 (Python Code)

Max Activating Token Index: 850

Text #16

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1463. Min Act: -0.0001

Data Index: 1625796 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0876. Min Act: -0.0002

Data Index: 914859 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0269. Min Act: -0.0001

Data Index: 39757 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1554. Min Act: -0.0001

Data Index: 1115650 (C4 (Web Text))

Max Activating Token Index: 940