Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 197 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1089839 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1311967 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9133. Min Act: -0.0000

Data Index: 319892 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9050. Min Act: -0.0000

Data Index: 100772 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8940. Min Act: -0.0000

Data Index: 547569 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8194. Min Act: -0.0000

Data Index: 170715 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1011396 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8224. Min Act: -0.0000

Data Index: 986940 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7986. Min Act: -0.0000

Data Index: 678334 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7974. Min Act: -0.0000

Data Index: 750714 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7129. Min Act: -0.0000

Data Index: 898197 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1285293 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8278. Min Act: -0.0000

Data Index: 369290 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7421. Min Act: -0.0000

Data Index: 61793 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1239529 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7266. Min Act: -0.0000

Data Index: 295085 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7495. Min Act: -0.0000

Data Index: 199704 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7248. Min Act: -0.0000

Data Index: 307459 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7149. Min Act: -0.0000

Data Index: 131793 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7135. Min Act: -0.0000

Data Index: 438043 (C4 (Web Text))

Max Activating Token Index: 763