Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5623 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1791. Min Range: -1.1791

Max Act: 1.1791. Min Act: -0.0000

Data Index: 257309 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.9202. Min Act: -0.0000

Data Index: 443845 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.8672. Min Act: -0.0000

Data Index: 97123 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.8365. Min Act: -0.0000

Data Index: 318438 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.7535. Min Act: -0.0000

Data Index: 591377 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.7747. Min Act: -0.0000

Data Index: 717167 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.7567. Min Act: -0.0000

Data Index: 846557 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1132580 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.7365. Min Act: -0.0000

Data Index: 827032 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1162576 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.6227. Min Act: -0.0000

Data Index: 17007 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1295943 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.5767. Min Act: -0.0000

Data Index: 5869 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.6311. Min Act: -0.0000

Data Index: 415205 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.5199. Min Act: -0.0000

Data Index: 41617 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.5617. Min Act: -0.0000

Data Index: 931447 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.5606. Min Act: -0.0000

Data Index: 270763 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.5562. Min Act: -0.0000

Data Index: 848053 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1431188 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 1.1791. Min Range: -1.1791

Max Act: 0.5704. Min Act: -0.0000

Data Index: 756208 (C4 (Web Text))

Max Activating Token Index: 302