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

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

Neuron 1108 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1126109 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1024173 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0546. Min Act: -0.0001

Data Index: 311199 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0482. Min Act: -0.0001

Data Index: 114473 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1157422 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0473. Min Act: -0.0002

Data Index: 187339 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0450. Min Act: -0.0001

Data Index: 828614 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0441. Min Act: -0.0001

Data Index: 596177 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1317599 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0466. Min Act: -0.0001

Data Index: 733052 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1316229 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1109931 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0416. Min Act: -0.0001

Data Index: 280004 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0414. Min Act: -0.0001

Data Index: 437806 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0416. Min Act: -0.0001

Data Index: 396195 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0404. Min Act: -0.0001

Data Index: 385509 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1073472 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1207117 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1251762 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0390. Min Act: -0.0001

Data Index: 662106 (C4 (Web Text))

Max Activating Token Index: 361