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

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

Neuron 483 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.9749. Min Act: -0.0000

Data Index: 773876 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.8302. Min Act: -0.0000

Data Index: 503709 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.8580. Min Act: -0.0001

Data Index: 385188 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.7894. Min Act: -0.0001

Data Index: 482558 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.7660. Min Act: -0.0000

Data Index: 252861 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.8170. Min Act: -0.0001

Data Index: 624821 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1237694 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.7406. Min Act: -0.0000

Data Index: 291391 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.7046. Min Act: -0.0001

Data Index: 928128 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.7280. Min Act: -0.0001

Data Index: 637044 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6768. Min Act: -0.0001

Data Index: 1151272 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1276935 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6880. Min Act: -0.0000

Data Index: 552021 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6469. Min Act: -0.0000

Data Index: 583469 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.7014. Min Act: -0.0000

Data Index: 217146 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6493. Min Act: -0.0000

Data Index: 115243 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6676. Min Act: -0.0001

Data Index: 498390 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6632. Min Act: -0.0000

Data Index: 30650 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6610. Min Act: -0.0000

Data Index: 966280 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.9749. Min Range: -0.9749

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1111491 (C4 (Web Text))

Max Activating Token Index: 935