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

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

Neuron 4602 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0971. Min Range: -1.0971

Max Act: 1.0971. Min Act: -0.0000

Data Index: 883132 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8988. Min Act: -0.0000

Data Index: 569143 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1194140 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1241338 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.7604. Min Act: -0.0000

Data Index: 308116 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.7161. Min Act: -0.0000

Data Index: 648536 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6861. Min Act: -0.0000

Data Index: 763404 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1214860 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6674. Min Act: -0.0000

Data Index: 634189 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6948. Min Act: -0.0000

Data Index: 668930 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6373. Min Act: -0.0000

Data Index: 435086 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6955. Min Act: -0.0000

Data Index: 256338 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6441. Min Act: -0.0000

Data Index: 396575 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6602. Min Act: -0.0000

Data Index: 722933 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6242. Min Act: -0.0000

Data Index: 897067 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6443. Min Act: -0.0000

Data Index: 656331 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6497. Min Act: -0.0000

Data Index: 221229 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6235. Min Act: -0.0000

Data Index: 837777 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.5546. Min Act: -0.0000

Data Index: 864370 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.6083. Min Act: -0.0000

Data Index: 116905 (C4 (Web Text))

Max Activating Token Index: 296