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

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

Neuron 1056 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3559. Min Range: -6.3559

Max Act: 6.0126. Min Act: -0.0000

Data Index: 722958 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 6.3559. Min Range: -6.3559

Max Act: 6.3559. Min Act: -0.0000

Data Index: 593960 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.8083. Min Act: -0.0000

Data Index: 1028579 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 6.3559. Min Range: -6.3559

Max Act: 6.1828. Min Act: -0.0000

Data Index: 95754 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 6.3559. Min Range: -6.3559

Max Act: 6.1661. Min Act: -0.0000

Data Index: 987451 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.7889. Min Act: -0.0000

Data Index: 1254840 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.4464. Min Act: -0.0000

Data Index: 1228921 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.8361. Min Act: -0.0000

Data Index: 905573 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.8246. Min Act: -0.0000

Data Index: 295230 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.5905. Min Act: -0.0000

Data Index: 657884 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.7732. Min Act: -0.0000

Data Index: 1214528 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.6601. Min Act: -0.0000

Data Index: 828583 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.4524. Min Act: -0.0000

Data Index: 702877 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.6573. Min Act: -0.0000

Data Index: 142150 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.8201. Min Act: -0.0000

Data Index: 1007277 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.4494. Min Act: -0.0000

Data Index: 569208 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.9963. Min Act: -0.0000

Data Index: 377033 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.4494. Min Act: -0.0000

Data Index: 304246 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.4552. Min Act: -0.0000

Data Index: 1343838 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 6.3559. Min Range: -6.3559

Max Act: 5.4394. Min Act: -0.0000

Data Index: 603965 (C4 (Web Text))

Max Activating Token Index: 364