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

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

Neuron 5571 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.3259. Min Act: -0.0000

Data Index: 770840 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1097257 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2331. Min Act: -0.0000

Data Index: 369683 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1651. Min Act: -0.0000

Data Index: 90124 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2064. Min Act: -0.0000

Data Index: 979133 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1174551 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1688. Min Act: -0.0000

Data Index: 151211 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1735. Min Act: -0.0000

Data Index: 152236 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1438. Min Act: -0.0000

Data Index: 729428 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1630. Min Act: -0.0000

Data Index: 838964 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1573. Min Act: -0.0000

Data Index: 412847 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1604. Min Act: -0.0000

Data Index: 239169 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1663. Min Act: -0.0000

Data Index: 20491 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1672. Min Act: -0.0000

Data Index: 462128 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1364. Min Act: -0.0000

Data Index: 129445 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1177459 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1498. Min Act: -0.0000

Data Index: 514104 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1635. Min Act: -0.0000

Data Index: 238453 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1445. Min Act: -0.0000

Data Index: 36282 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1435. Min Act: -0.0000

Data Index: 36749 (C4 (Web Text))

Max Activating Token Index: 551