Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4947 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.5233. Min Act: -0.0001

Data Index: 1198784 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.6876. Min Act: -0.0001

Data Index: 828167 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.4406. Min Act: -0.0001

Data Index: 320316 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.5611. Min Act: -0.0001

Data Index: 537817 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.3554. Min Act: -0.0001

Data Index: 1061638 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.2600. Min Act: -0.0001

Data Index: 669457 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.3038. Min Act: -0.0001

Data Index: 867049 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.3634. Min Act: -0.0001

Data Index: 272019 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.2107. Min Act: -0.0001

Data Index: 1286901 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.2510. Min Act: -0.0001

Data Index: 303408 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.1932. Min Act: -0.0001

Data Index: 1290636 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.1386. Min Act: -0.0001

Data Index: 692200 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.0964. Min Act: -0.0001

Data Index: 31830 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.2057. Min Act: -0.0001

Data Index: 82579 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.0764. Min Act: -0.0001

Data Index: 164110 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.1680. Min Act: -0.0001

Data Index: 62812 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.0486. Min Act: -0.0001

Data Index: 890640 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.1451. Min Act: -0.0001

Data Index: 691552 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 1.6876. Min Range: -1.6876

Max Act: 1.0300. Min Act: -0.0001

Data Index: 1338478 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.6876. Min Range: -1.6876

Max Act: 0.9812. Min Act: -0.0001

Data Index: 159393 (C4 (Web Text))

Max Activating Token Index: 770