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

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

Neuron 2229 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1460322 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0376. Min Act: -0.0000

Data Index: 236031 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0300. Min Act: -0.0000

Data Index: 1624643 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0308. Min Act: -0.0000

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0304. Min Act: -0.0000

Data Index: 409194 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0280. Min Act: -0.0000

Data Index: 37836 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0287. Min Act: -0.0000

Data Index: 762935 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0306. Min Act: -0.0000

Data Index: 522974 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0294. Min Act: -0.0000

Data Index: 74757 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0293. Min Act: -0.0000

Data Index: 876574 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0288. Min Act: -0.0000

Data Index: 1585017 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1245513 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0270. Min Act: -0.0000

Data Index: 225479 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1384998 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0273. Min Act: -0.0000

Data Index: 1044465 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0291. Min Act: -0.0000

Data Index: 197258 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0282. Min Act: -0.0000

Data Index: 512444 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0285. Min Act: -0.0000

Data Index: 741142 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1142943 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0282. Min Act: -0.0000

Data Index: 1284129 (C4 (Web Text))

Max Activating Token Index: 550