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

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

Neuron 2630 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.1676. Min Act: -0.0000

Data Index: 857919 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9799. Min Act: -0.0000

Data Index: 563591 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1100076 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9205. Min Act: -0.0000

Data Index: 509557 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8641. Min Act: -0.0000

Data Index: 413604 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7973. Min Act: -0.0000

Data Index: 173202 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8327. Min Act: -0.0000

Data Index: 226858 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8640. Min Act: -0.0000

Data Index: 135351 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8390. Min Act: -0.0000

Data Index: 967927 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8336. Min Act: -0.0000

Data Index: 997430 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1118631 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8218. Min Act: -0.0000

Data Index: 719267 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8403. Min Act: -0.0000

Data Index: 245961 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1099835 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7992. Min Act: -0.0000

Data Index: 59839 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7215. Min Act: -0.0000

Data Index: 86090 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7472. Min Act: -0.0000

Data Index: 329565 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7467. Min Act: -0.0000

Data Index: 32081 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1277375 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7442. Min Act: -0.0000

Data Index: 363638 (C4 (Web Text))

Max Activating Token Index: 128