Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 306 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0506. Min Act: -0.0006

Data Index: 851486 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0489. Min Act: -0.0005

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0005

Data Index: 258146 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0466. Min Act: -0.0006

Data Index: 1173345 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0503. Min Act: -0.0005

Data Index: 186949 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0422. Min Act: -0.0006

Data Index: 700496 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0467. Min Act: -0.0006

Data Index: 610063 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0460. Min Act: -0.0006

Data Index: 140051 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0430. Min Act: -0.0006

Data Index: 743619 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0414. Min Act: -0.0006

Data Index: 54515 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0386. Min Act: -0.0006

Data Index: 46142 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0398. Min Act: -0.0006

Data Index: 448272 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0439. Min Act: -0.0006

Data Index: 924992 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1027568 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0455. Min Act: -0.0005

Data Index: 452373 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0435. Min Act: -0.0006

Data Index: 904375 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0418. Min Act: -0.0005

Data Index: 654174 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0425. Min Act: -0.0006

Data Index: 933270 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0416. Min Act: -0.0006

Data Index: 994909 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0442. Min Act: -0.0005

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 523