Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1565 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.3286. Min Act: -0.0001

Data Index: 1276381 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.3755. Min Act: -0.0001

Data Index: 718721 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.3016. Min Act: -0.0001

Data Index: 658622 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.2613. Min Act: -0.0001

Data Index: 430449 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.2215. Min Act: -0.0000

Data Index: 426256 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.2213. Min Act: -0.0001

Data Index: 1281080 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1073719 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.1621. Min Act: -0.0001

Data Index: 238501 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.1590. Min Act: -0.0001

Data Index: 356465 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.0588. Min Act: -0.0001

Data Index: 1089115 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.0885. Min Act: -0.0001

Data Index: 807214 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.0431. Min Act: -0.0001

Data Index: 1086069 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.0761. Min Act: -0.0001

Data Index: 1205318 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1318242 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.1009. Min Act: -0.0001

Data Index: 163341 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.0215. Min Act: -0.0001

Data Index: 1286709 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 1.3755. Min Range: -1.3755

Max Act: 1.0734. Min Act: -0.0001

Data Index: 622071 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.3755. Min Range: -1.3755

Max Act: 0.9840. Min Act: -0.0001

Data Index: 1035498 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.3755. Min Range: -1.3755

Max Act: 0.9867. Min Act: -0.0001

Data Index: 590438 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 1.3755. Min Range: -1.3755

Max Act: 0.9456. Min Act: -0.0000

Data Index: 746700 (C4 (Web Text))

Max Activating Token Index: 183