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

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

Neuron 3027 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2693. Min Range: -3.2693

Max Act: 3.2693. Min Act: -0.0001

Data Index: 1345693 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.8009. Min Act: -0.0001

Data Index: 101036 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.5478. Min Act: -0.0001

Data Index: 784518 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.2124. Min Act: -0.0001

Data Index: 540657 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.3751. Min Act: -0.0001

Data Index: 236861 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.3626. Min Act: -0.0001

Data Index: 612713 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.2230. Min Act: -0.0001

Data Index: 9932 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.3364. Min Act: -0.0001

Data Index: 627107 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.2941. Min Act: -0.0001

Data Index: 967150 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.0969. Min Act: -0.0001

Data Index: 1292186 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.0971. Min Act: -0.0001

Data Index: 887932 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.2146. Min Act: -0.0000

Data Index: 226998 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.1718. Min Act: -0.0001

Data Index: 788956 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.1621. Min Act: -0.0001

Data Index: 691986 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.1084. Min Act: -0.0001

Data Index: 239835 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.1196. Min Act: -0.0001

Data Index: 1345462 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.1243. Min Act: -0.0000

Data Index: 158189 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.0449. Min Act: -0.0001

Data Index: 697124 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.1590. Min Act: -0.0001

Data Index: 1138183 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 3.2693. Min Range: -3.2693

Max Act: 2.0031. Min Act: -0.0001

Data Index: 521113 (C4 (Web Text))

Max Activating Token Index: 936