Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2352 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0004

Data Index: 527806 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0302. Min Act: -0.0004

Data Index: 5784 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0004

Data Index: 91519 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0261. Min Act: -0.0004

Data Index: 685456 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0299. Min Act: -0.0004

Data Index: 635694 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0311. Min Act: -0.0004

Data Index: 34202 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0277. Min Act: -0.0004

Data Index: 503801 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0237. Min Act: -0.0004

Data Index: 65575 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0004

Data Index: 1028759 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0296. Min Act: -0.0004

Data Index: 777388 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0004

Data Index: 1183299 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0292. Min Act: -0.0004

Data Index: 821278 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0290. Min Act: -0.0004

Data Index: 1290648 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0285. Min Act: -0.0004

Data Index: 1167501 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0316. Min Act: -0.0004

Data Index: 901120 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0286. Min Act: -0.0004

Data Index: 786502 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0310. Min Act: -0.0004

Data Index: 1357964 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0280. Min Act: -0.0004

Data Index: 603289 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0311. Min Act: -0.0004

Data Index: 335350 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0004

Data Index: 744318 (C4 (Web Text))

Max Activating Token Index: 963