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

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

Neuron 5607 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.7005. Min Act: -0.0000

Data Index: 1177641 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.5812. Min Act: -0.0000

Data Index: 1013353 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.4642. Min Act: -0.0000

Data Index: 1078723 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3621. Min Act: -0.0000

Data Index: 719467 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.4088. Min Act: -0.0000

Data Index: 80714 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3191. Min Act: -0.0000

Data Index: 980729 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.4105. Min Act: -0.0000

Data Index: 301508 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3269. Min Act: -0.0000

Data Index: 330725 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3338. Min Act: -0.0000

Data Index: 7393 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2963. Min Act: -0.0000

Data Index: 282995 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1222479 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2896. Min Act: -0.0000

Data Index: 46589 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3270. Min Act: -0.0000

Data Index: 73790 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2816. Min Act: -0.0000

Data Index: 789276 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2643. Min Act: -0.0000

Data Index: 213489 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2972. Min Act: -0.0000

Data Index: 1286427 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3372. Min Act: -0.0000

Data Index: 219404 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3067. Min Act: -0.0000

Data Index: 440394 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3689. Min Act: -0.0000

Data Index: 123143 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3050. Min Act: -0.0000

Data Index: 1337064 (C4 (Web Text))

Max Activating Token Index: 542