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

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

Neuron 267 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.9352. Min Act: -0.0000

Data Index: 838205 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1130276 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.8080. Min Act: -0.0001

Data Index: 137238 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1323864 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.7304. Min Act: -0.0000

Data Index: 580517 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6681. Min Act: -0.0000

Data Index: 261541 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1265358 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6203. Min Act: -0.0000

Data Index: 495062 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5938. Min Act: -0.0001

Data Index: 645673 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5935. Min Act: -0.0000

Data Index: 851630 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6003. Min Act: -0.0000

Data Index: 672953 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1282410 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1358940 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5701. Min Act: -0.0001

Data Index: 1316997 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5666. Min Act: -0.0001

Data Index: 678452 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5781. Min Act: -0.0001

Data Index: 966682 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5770. Min Act: -0.0000

Data Index: 524139 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5537. Min Act: -0.0000

Data Index: 882401 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5317. Min Act: -0.0000

Data Index: 531075 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.5670. Min Act: -0.0000

Data Index: 535847 (C4 (Web Text))

Max Activating Token Index: 557