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

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

Neuron 950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.9618. Min Act: -0.0001

Data Index: 135299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.9374. Min Act: -0.0001

Data Index: 568539 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.9153. Min Act: -0.0001

Data Index: 372888 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6683. Min Act: -0.0001

Data Index: 1030130 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.8331. Min Act: -0.0001

Data Index: 511750 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.3348. Min Act: -0.0000

Data Index: 888027 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6386. Min Act: -0.0001

Data Index: 891354 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6014. Min Act: -0.0000

Data Index: 1491503 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5481. Min Act: -0.0001

Data Index: 1197815 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4859. Min Act: -0.0000

Data Index: 1004357 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.3808. Min Act: -0.0000

Data Index: 1467645 (Python Code)

Max Activating Token Index: 356

Text #11

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1367606 (Python Code)

Max Activating Token Index: 560

Text #12

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1624483 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5380. Min Act: -0.0001

Data Index: 64868 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4413. Min Act: -0.0000

Data Index: 1394112 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5520. Min Act: -0.0000

Data Index: 1440630 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4930. Min Act: -0.0000

Data Index: 500848 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1591496 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1222591 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1546220 (Python Code)

Max Activating Token Index: 333