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

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

Neuron 3852 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2247. Min Act: -0.0001

Data Index: 1355450 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2304. Min Act: -0.0001

Data Index: 331075 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2006. Min Act: -0.0001

Data Index: 788318 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2079. Min Act: -0.0001

Data Index: 74781 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1978. Min Act: -0.0001

Data Index: 717584 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1237065 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1150822 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1794. Min Act: -0.0001

Data Index: 990722 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1782. Min Act: -0.0001

Data Index: 960411 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1729. Min Act: -0.0001

Data Index: 324187 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1754. Min Act: -0.0001

Data Index: 800511 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1008739 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1646. Min Act: -0.0001

Data Index: 211857 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1628. Min Act: -0.0001

Data Index: 459542 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1261340 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1581. Min Act: -0.0001

Data Index: 8798 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1072794 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1510. Min Act: -0.0001

Data Index: 372371 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1494. Min Act: -0.0001

Data Index: 738214 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1486. Min Act: -0.0001

Data Index: 520281 (C4 (Web Text))

Max Activating Token Index: 1020