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

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

Neuron 507 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0002

Data Index: 710614 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1589167 (Python Code)

Max Activating Token Index: 256

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1640712 (Python Code)

Max Activating Token Index: 233

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1382748 (Python Code)

Max Activating Token Index: 82

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1651916 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1017621 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0377. Min Act: -0.0002

Data Index: 507319 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1389345 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1579439 (Python Code)

Max Activating Token Index: 648

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1123347 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0366. Min Act: -0.0002

Data Index: 612900 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0364. Min Act: -0.0002

Data Index: 724530 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0344. Min Act: -0.0002

Data Index: 488606 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0360. Min Act: -0.0002

Data Index: 147517 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1143042 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0344. Min Act: -0.0002

Data Index: 140180 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1292515 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0343. Min Act: -0.0002

Data Index: 135090 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0336. Min Act: -0.0002

Data Index: 310494 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1603583 (Python Code)

Max Activating Token Index: 82