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

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

Neuron 4456 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1116640 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0535. Min Act: -0.0001

Data Index: 745540 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0590. Min Act: -0.0001

Data Index: 535223 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0557. Min Act: -0.0001

Data Index: 388148 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0512. Min Act: -0.0001

Data Index: 3162 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1218313 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0448. Min Act: -0.0001

Data Index: 40484 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0463. Min Act: -0.0001

Data Index: 684266 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0491. Min Act: -0.0001

Data Index: 260109 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0563. Min Act: -0.0001

Data Index: 80825 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0549. Min Act: -0.0001

Data Index: 38856 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1094163 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1275202 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0532. Min Act: -0.0001

Data Index: 876669 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0451. Min Act: -0.0001

Data Index: 636528 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1549528 (Python Code)

Max Activating Token Index: 354

Text #16

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0463. Min Act: -0.0001

Data Index: 785608 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0461. Min Act: -0.0001

Data Index: 791788 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0516. Min Act: -0.0001

Data Index: 548291 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1048619 (C4 (Web Text))

Max Activating Token Index: 412