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

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

Neuron 4656 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6108. Min Act: -0.0000

Data Index: 136974 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5361. Min Act: -0.0000

Data Index: 686189 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1010024 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3970. Min Act: -0.0000

Data Index: 409680 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3595. Min Act: -0.0000

Data Index: 307889 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4013. Min Act: -0.0000

Data Index: 448705 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1245073 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3495. Min Act: -0.0000

Data Index: 741636 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1339133 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3765. Min Act: -0.0000

Data Index: 503680 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3855. Min Act: -0.0000

Data Index: 308650 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1134931 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1101753 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3550. Min Act: -0.0000

Data Index: 942219 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.2956. Min Act: -0.0000

Data Index: 567220 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3495. Min Act: -0.0000

Data Index: 670468 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3257. Min Act: -0.0000

Data Index: 495002 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3174. Min Act: -0.0000

Data Index: 862430 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3297. Min Act: -0.0000

Data Index: 61426 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1195647 (C4 (Web Text))

Max Activating Token Index: 310