Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 58 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0814. Min Act: -0.0000

Data Index: 187278 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1407441 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0649. Min Act: -0.0001

Data Index: 43780 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0685. Min Act: -0.0001

Data Index: 180403 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0574. Min Act: -0.0000

Data Index: 316679 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1158889 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0561. Min Act: -0.0001

Data Index: 760282 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0595. Min Act: -0.0000

Data Index: 1217307 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0705. Min Act: -0.0001

Data Index: 717467 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0538. Min Act: -0.0000

Data Index: 282655 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0578. Min Act: -0.0000

Data Index: 787935 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0573. Min Act: -0.0000

Data Index: 314472 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0526. Min Act: 0.0000

Data Index: 676851 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1170319 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1080066 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0611. Min Act: -0.0001

Data Index: 265454 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0561. Min Act: -0.0001

Data Index: 209094 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1279270 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0545. Min Act: -0.0000

Data Index: 891798 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0494. Min Act: -0.0001

Data Index: 909518 (C4 (Web Text))

Max Activating Token Index: 437