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

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

Neuron 4251 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: 0.0810. Min Range: -0.0810

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1263947 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0000

Data Index: 126005 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0702. Min Act: -0.0000

Data Index: 2547 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0743. Min Act: -0.0000

Data Index: 294235 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0727. Min Act: -0.0000

Data Index: 972441 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0711. Min Act: -0.0000

Data Index: 356961 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0675. Min Act: -0.0000

Data Index: 14997 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0663. Min Act: -0.0000

Data Index: 342379 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1534378 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0638. Min Act: -0.0000

Data Index: 131402 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0678. Min Act: -0.0000

Data Index: 916247 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0649. Min Act: -0.0000

Data Index: 32995 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1478603 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0671. Min Act: -0.0000

Data Index: 284253 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1130365 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0615. Min Act: -0.0000

Data Index: 438646 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1025560 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0597. Min Act: -0.0000

Data Index: 587528 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0561. Min Act: -0.0000

Data Index: 308167 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0624. Min Act: -0.0000

Data Index: 778884 (C4 (Web Text))

Max Activating Token Index: 182