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

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

Neuron 4583 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0001

Data Index: 174895 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0591. Min Act: -0.0001

Data Index: 914618 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0649. Min Act: -0.0001

Data Index: 70432 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0619. Min Act: -0.0001

Data Index: 538723 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0613. Min Act: -0.0001

Data Index: 249446 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0509. Min Act: -0.0001

Data Index: 200020 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0621. Min Act: -0.0001

Data Index: 516111 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1323066 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0587. Min Act: -0.0001

Data Index: 589881 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0560. Min Act: -0.0001

Data Index: 867193 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0595. Min Act: -0.0001

Data Index: 734175 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0534. Min Act: -0.0001

Data Index: 86766 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1205927 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0546. Min Act: -0.0001

Data Index: 989024 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0546. Min Act: -0.0001

Data Index: 665705 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0610. Min Act: -0.0001

Data Index: 285681 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1655061 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0574. Min Act: -0.0001

Data Index: 166801 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0555. Min Act: -0.0001

Data Index: 183196 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0509. Min Act: -0.0001

Data Index: 128960 (C4 (Web Text))

Max Activating Token Index: 744