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

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

Neuron 3183 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: 6.1958. Min Range: -6.1958

Max Act: 6.1958. Min Act: -0.0000

Data Index: 123796 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 6.1958. Min Range: -6.1958

Max Act: 6.0245. Min Act: -0.0000

Data Index: 1292287 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 6.1958. Min Range: -6.1958

Max Act: 5.5736. Min Act: -0.0000

Data Index: 1022290 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 6.1958. Min Range: -6.1958

Max Act: 5.6498. Min Act: -0.0000

Data Index: 1239987 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 6.1958. Min Range: -6.1958

Max Act: 5.3419. Min Act: -0.0000

Data Index: 1339683 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 6.1958. Min Range: -6.1958

Max Act: 5.0052. Min Act: -0.0001

Data Index: 555687 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 6.1958. Min Range: -6.1958

Max Act: 5.0298. Min Act: -0.0000

Data Index: 935969 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.8030. Min Act: -0.0000

Data Index: 367386 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.7515. Min Act: -0.0000

Data Index: 1012805 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.4608. Min Act: -0.0000

Data Index: 1292514 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 6.1958. Min Range: -6.1958

Max Act: 5.3732. Min Act: -0.0000

Data Index: 150671 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.8825. Min Act: -0.0000

Data Index: 761943 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.5391. Min Act: -0.0000

Data Index: 1109765 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.5047. Min Act: -0.0000

Data Index: 283293 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.5791. Min Act: -0.0000

Data Index: 372541 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.8868. Min Act: -0.0000

Data Index: 171149 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.1028. Min Act: -0.0000

Data Index: 534152 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.2285. Min Act: -0.0000

Data Index: 625894 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.1707. Min Act: -0.0000

Data Index: 1120955 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 6.1958. Min Range: -6.1958

Max Act: 4.2455. Min Act: -0.0000

Data Index: 220722 (C4 (Web Text))

Max Activating Token Index: 660