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

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

Neuron 3205 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4680. Min Range: -1.4680

Max Act: 1.4680. Min Act: -0.0001

Data Index: 666707 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.4680. Min Range: -1.4680

Max Act: 1.4273. Min Act: -0.0001

Data Index: 418476 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.4680. Min Range: -1.4680

Max Act: 1.2703. Min Act: -0.0001

Data Index: 577022 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.4680. Min Range: -1.4680

Max Act: 1.4000. Min Act: -0.0001

Data Index: 1255435 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.4680. Min Range: -1.4680

Max Act: 1.1111. Min Act: -0.0001

Data Index: 1212392 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.9919. Min Act: -0.0001

Data Index: 1356220 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1347321 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.4680. Min Range: -1.4680

Max Act: 1.0475. Min Act: -0.0001

Data Index: 515505 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.8344. Min Act: -0.0001

Data Index: 546981 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.9807. Min Act: -0.0001

Data Index: 493553 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.4680. Min Range: -1.4680

Max Act: 1.0485. Min Act: -0.0001

Data Index: 541322 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.9541. Min Act: -0.0001

Data Index: 273874 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.9076. Min Act: -0.0001

Data Index: 791755 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.4680. Min Range: -1.4680

Max Act: 1.0167. Min Act: -0.0001

Data Index: 341295 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.9080. Min Act: -0.0000

Data Index: 750902 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.9102. Min Act: -0.0001

Data Index: 134530 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.8990. Min Act: -0.0001

Data Index: 943651 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.8836. Min Act: -0.0001

Data Index: 354277 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.9736. Min Act: -0.0000

Data Index: 699490 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 1.4680. Min Range: -1.4680

Max Act: 0.8789. Min Act: -0.0001

Data Index: 897588 (C4 (Web Text))

Max Activating Token Index: 1011