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

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

Neuron 5853 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.4351. Min Act: -0.0000

Data Index: 719555 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1421. Min Act: -0.0000

Data Index: 590839 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.2606. Min Act: -0.0000

Data Index: 26038 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1029. Min Act: -0.0000

Data Index: 383719 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1574. Min Act: 0.0000

Data Index: 321360 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.2050. Min Act: -0.0000

Data Index: 1151813 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1171. Min Act: -0.0000

Data Index: 1276162 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.0157. Min Act: -0.0000

Data Index: 151045 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.0960. Min Act: -0.0000

Data Index: 152176 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.9528. Min Act: 0.0000

Data Index: 259198 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.0544. Min Act: -0.0000

Data Index: 642043 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1354991 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.9452. Min Act: -0.0000

Data Index: 565961 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1271055 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1182352 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.9336. Min Act: -0.0000

Data Index: 230146 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.8529. Min Act: -0.0000

Data Index: 773390 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.9469. Min Act: -0.0000

Data Index: 827999 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.8888. Min Act: -0.0000

Data Index: 115802 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.4351. Min Range: -1.4351

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1125602 (C4 (Web Text))

Max Activating Token Index: 105