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

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

Neuron 5194 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.3026. Min Act: -0.0000

Data Index: 911308 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2798. Min Act: -0.0000

Data Index: 732353 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2681. Min Act: -0.0000

Data Index: 41255 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2651. Min Act: -0.0000

Data Index: 179919 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2436. Min Act: -0.0000

Data Index: 188386 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2696. Min Act: -0.0000

Data Index: 665071 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2579. Min Act: -0.0000

Data Index: 814850 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1267478 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1134530 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1040978 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2357. Min Act: -0.0000

Data Index: 60225 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2503. Min Act: -0.0000

Data Index: 948401 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1176830 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2493. Min Act: -0.0000

Data Index: 368751 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2245. Min Act: -0.0000

Data Index: 267047 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2342. Min Act: -0.0000

Data Index: 684807 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2317. Min Act: -0.0000

Data Index: 396467 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2353. Min Act: -0.0000

Data Index: 49314 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2255. Min Act: -0.0000

Data Index: 672325 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1261205 (C4 (Web Text))

Max Activating Token Index: 263