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

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

Neuron 3518 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0541. Min Range: -2.0541

Max Act: 2.0541. Min Act: -0.0000

Data Index: 860268 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.7828. Min Act: -0.0000

Data Index: 96423 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.7871. Min Act: -0.0000

Data Index: 1158293 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.7332. Min Act: -0.0001

Data Index: 303994 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.7245. Min Act: -0.0000

Data Index: 315415 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6959. Min Act: -0.0000

Data Index: 575837 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6647. Min Act: -0.0000

Data Index: 733601 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6591. Min Act: -0.0000

Data Index: 661403 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6447. Min Act: -0.0000

Data Index: 1003634 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.7256. Min Act: -0.0000

Data Index: 102893 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6308. Min Act: -0.0001

Data Index: 133010 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.7235. Min Act: -0.0001

Data Index: 592316 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.7028. Min Act: -0.0000

Data Index: 833368 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6135. Min Act: -0.0000

Data Index: 790287 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6034. Min Act: -0.0000

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.5060. Min Act: -0.0001

Data Index: 1298856 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6701. Min Act: -0.0000

Data Index: 707980 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6495. Min Act: -0.0001

Data Index: 1045859 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6378. Min Act: -0.0000

Data Index: 149325 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 2.0541. Min Range: -2.0541

Max Act: 1.6421. Min Act: -0.0000

Data Index: 1016287 (C4 (Web Text))

Max Activating Token Index: 1012