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

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

Neuron 3071 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0873. Min Act: -0.0000

Data Index: 503649 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0552. Min Act: -0.0000

Data Index: 187114 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0530. Min Act: -0.0001

Data Index: 791127 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0536. Min Act: -0.0000

Data Index: 928610 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0563. Min Act: -0.0001

Data Index: 700004 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0515. Min Act: -0.0000

Data Index: 525817 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0529. Min Act: -0.0001

Data Index: 613809 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1082218 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0498. Min Act: -0.0000

Data Index: 620495 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1061811 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0493. Min Act: -0.0000

Data Index: 720336 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0464. Min Act: -0.0000

Data Index: 381940 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1084395 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0406. Min Act: -0.0001

Data Index: 969500 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0436. Min Act: -0.0000

Data Index: 154417 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0448. Min Act: -0.0000

Data Index: 694360 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0423. Min Act: -0.0001

Data Index: 687206 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1158821 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0441. Min Act: -0.0001

Data Index: 861531 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1241377 (C4 (Web Text))

Max Activating Token Index: 249