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

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

Neuron 662 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: 0.6310. Min Range: -0.6310

Max Act: 0.6310. Min Act: -0.0000

Data Index: 930177 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5726. Min Act: -0.0001

Data Index: 1353165 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5910. Min Act: -0.0001

Data Index: 1239382 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5174. Min Act: -0.0001

Data Index: 415854 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5128. Min Act: -0.0001

Data Index: 185105 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5054. Min Act: -0.0000

Data Index: 426160 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5008. Min Act: -0.0000

Data Index: 859572 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4915. Min Act: -0.0000

Data Index: 420522 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4748. Min Act: -0.0000

Data Index: 780563 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1122792 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4405. Min Act: -0.0001

Data Index: 255655 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4681. Min Act: -0.0001

Data Index: 1225078 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4441. Min Act: -0.0000

Data Index: 795786 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4499. Min Act: -0.0001

Data Index: 936160 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4443. Min Act: -0.0000

Data Index: 293127 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4422. Min Act: -0.0001

Data Index: 412463 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4440. Min Act: -0.0001

Data Index: 497697 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4129. Min Act: -0.0000

Data Index: 688814 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.3983. Min Act: -0.0000

Data Index: 782461 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1246385 (C4 (Web Text))

Max Activating Token Index: 126