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

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

Neuron 1875 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1339252 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1028324 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4671. Min Act: -0.0001

Data Index: 533060 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1100944 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4279. Min Act: -0.0000

Data Index: 817385 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4530. Min Act: -0.0000

Data Index: 265789 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4317. Min Act: -0.0000

Data Index: 778590 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4448. Min Act: -0.0001

Data Index: 1153077 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1158060 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4417. Min Act: -0.0000

Data Index: 689086 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4118. Min Act: -0.0001

Data Index: 868463 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3895. Min Act: -0.0001

Data Index: 854493 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3767. Min Act: -0.0000

Data Index: 67867 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3615. Min Act: -0.0000

Data Index: 148449 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1120150 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3740. Min Act: -0.0000

Data Index: 546443 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3471. Min Act: -0.0000

Data Index: 300079 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3598. Min Act: -0.0000

Data Index: 107870 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3810. Min Act: -0.0001

Data Index: 65382 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3711. Min Act: -0.0001

Data Index: 122707 (C4 (Web Text))

Max Activating Token Index: 40