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

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

Neuron 4408 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.3981. Min Act: -0.0000

Data Index: 697415 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1016864 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1169002 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1069492 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.1345. Min Act: -0.0000

Data Index: 584497 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1232189 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0444. Min Act: -0.0001

Data Index: 175484 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1254758 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0431. Min Act: -0.0000

Data Index: 656391 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0424. Min Act: -0.0000

Data Index: 989260 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0424. Min Act: -0.0000

Data Index: 145147 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0335. Min Act: -0.0000

Data Index: 935323 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0205. Min Act: -0.0000

Data Index: 379603 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0911. Min Act: -0.0000

Data Index: 681081 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9600. Min Act: -0.0000

Data Index: 273727 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0090. Min Act: -0.0001

Data Index: 363520 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0036. Min Act: -0.0000

Data Index: 1011471 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9971. Min Act: -0.0001

Data Index: 255195 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9994. Min Act: -0.0000

Data Index: 263687 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9713. Min Act: -0.0000

Data Index: 869022 (C4 (Web Text))

Max Activating Token Index: 98