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

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

Neuron 705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0534. Min Act: -0.0001

Data Index: 612600 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1628660 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0477. Min Act: -0.0001

Data Index: 993044 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0491. Min Act: -0.0001

Data Index: 216486 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0431. Min Act: -0.0001

Data Index: 792013 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1350641 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1520774 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0458. Min Act: -0.0001

Data Index: 987768 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0438. Min Act: -0.0001

Data Index: 296041 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0429. Min Act: -0.0001

Data Index: 568628 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1185450 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0403. Min Act: -0.0001

Data Index: 827247 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1123081 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1397851 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1110942 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0394. Min Act: -0.0001

Data Index: 583912 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1345223 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0360. Min Act: -0.0001

Data Index: 22000 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0376. Min Act: -0.0001

Data Index: 518412 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0377. Min Act: -0.0001

Data Index: 901497 (C4 (Web Text))

Max Activating Token Index: 957