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

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

Neuron 1015 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1138096 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.4520. Min Act: -0.0000

Data Index: 216730 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1516934 (Python Code)

Max Activating Token Index: 963

Text #3

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.4292. Min Act: -0.0000

Data Index: 633081 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1351970 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1189145 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.4106. Min Act: -0.0000

Data Index: 876419 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1363241 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3845. Min Act: -0.0000

Data Index: 15554 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1497958 (Python Code)

Max Activating Token Index: 355

Text #10

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1606184 (Python Code)

Max Activating Token Index: 374

Text #11

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3428. Min Act: -0.0000

Data Index: 720011 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1560420 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3614. Min Act: -0.0000

Data Index: 877186 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3690. Min Act: -0.0000

Data Index: 736691 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1142834 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3322. Min Act: -0.0000

Data Index: 997501 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3311. Min Act: -0.0000

Data Index: 409006 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1454183 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 0.4565. Min Range: -0.4565

Max Act: 0.3243. Min Act: -0.0000

Data Index: 827487 (C4 (Web Text))

Max Activating Token Index: 396