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

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

Neuron 4640 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: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1005933 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1547. Min Act: -0.0000

Data Index: 966048 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1553. Min Act: -0.0000

Data Index: 312611 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1549. Min Act: -0.0000

Data Index: 976426 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1543. Min Act: -0.0000

Data Index: 682228 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1348821 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1516. Min Act: -0.0000

Data Index: 389079 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1561. Min Act: -0.0000

Data Index: 480442 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1510. Min Act: -0.0000

Data Index: 534188 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1204491 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1591. Min Act: -0.0000

Data Index: 901916 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1529. Min Act: -0.0000

Data Index: 350179 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1253453 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1441. Min Act: -0.0000

Data Index: 18047 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1327019 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1388. Min Act: -0.0000

Data Index: 96173 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1307830 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1366. Min Act: -0.0000

Data Index: 19667 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1362. Min Act: -0.0000

Data Index: 2143 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1142255 (C4 (Web Text))

Max Activating Token Index: 615