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

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

Neuron 2527 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.7624. Min Act: -0.0000

Data Index: 29503 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.7233. Min Act: -0.0000

Data Index: 646593 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.1671. Min Act: -0.0000

Data Index: 276589 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.0410. Min Act: -0.0000

Data Index: 822232 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.2381. Min Act: -0.0000

Data Index: 197564 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.2096. Min Act: -0.0000

Data Index: 533337 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.2104. Min Act: -0.0000

Data Index: 615844 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.1770. Min Act: -0.0000

Data Index: 1030885 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.1358. Min Act: -0.0000

Data Index: 597083 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.1327. Min Act: -0.0000

Data Index: 635337 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 2.7624. Min Range: -2.7624

Max Act: 1.9862. Min Act: -0.0000

Data Index: 1111741 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.0796. Min Act: -0.0000

Data Index: 565735 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 2.7624. Min Range: -2.7624

Max Act: 1.8678. Min Act: -0.0000

Data Index: 814715 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.0516. Min Act: -0.0000

Data Index: 246144 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 2.7624. Min Range: -2.7624

Max Act: 1.9495. Min Act: -0.0000

Data Index: 890672 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.0564. Min Act: -0.0000

Data Index: 1296854 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 2.7624. Min Range: -2.7624

Max Act: 1.9315. Min Act: -0.0000

Data Index: 769700 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 2.7624. Min Range: -2.7624

Max Act: 1.9729. Min Act: -0.0000

Data Index: 690074 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 2.7624. Min Range: -2.7624

Max Act: 2.0703. Min Act: -0.0000

Data Index: 1140981 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 2.7624. Min Range: -2.7624

Max Act: 1.9308. Min Act: -0.0000

Data Index: 567287 (C4 (Web Text))

Max Activating Token Index: 357