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

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

Neuron 3932 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: 0.3772. Min Range: -0.3772

Max Act: 0.3703. Min Act: -0.0001

Data Index: 323344 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3698. Min Act: -0.0001

Data Index: 884897 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3680. Min Act: -0.0000

Data Index: 90273 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3772. Min Act: -0.0001

Data Index: 587977 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3178. Min Act: -0.0001

Data Index: 484663 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3608. Min Act: -0.0001

Data Index: 224892 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3546. Min Act: -0.0001

Data Index: 298641 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3580. Min Act: -0.0001

Data Index: 405272 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3713. Min Act: -0.0001

Data Index: 270673 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3051. Min Act: -0.0001

Data Index: 157076 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3042. Min Act: -0.0001

Data Index: 34558 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3368. Min Act: -0.0001

Data Index: 777002 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3442. Min Act: -0.0001

Data Index: 351167 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1233720 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3286. Min Act: -0.0001

Data Index: 987252 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3179. Min Act: -0.0001

Data Index: 324046 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3235. Min Act: -0.0001

Data Index: 663637 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3452. Min Act: -0.0001

Data Index: 584220 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2906. Min Act: -0.0001

Data Index: 1318333 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3219. Min Act: -0.0001

Data Index: 1288323 (C4 (Web Text))

Max Activating Token Index: 534