Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.2193. Min Act: -0.0000

Data Index: 314697 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1989. Min Act: -0.0000

Data Index: 814032 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1173580 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1013609 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1713. Min Act: -0.0000

Data Index: 868044 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1727. Min Act: -0.0000

Data Index: 990347 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1682. Min Act: -0.0000

Data Index: 578817 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1639. Min Act: -0.0000

Data Index: 270647 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1154268 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1543. Min Act: -0.0000

Data Index: 251831 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1583. Min Act: -0.0000

Data Index: 1200671 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1571. Min Act: -0.0000

Data Index: 883145 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1569. Min Act: -0.0000

Data Index: 906425 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1552. Min Act: -0.0000

Data Index: 931679 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1348885 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1523. Min Act: -0.0000

Data Index: 647633 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1547. Min Act: -0.0000

Data Index: 588975 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1457. Min Act: -0.0000

Data Index: 22201 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1446. Min Act: -0.0000

Data Index: 707343 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1376. Min Act: -0.0000

Data Index: 790981 (C4 (Web Text))

Max Activating Token Index: 459