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

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

Neuron 1038 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3472. Min Range: -4.3472

Max Act: 4.3472. Min Act: -0.0001

Data Index: 885019 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 4.3472. Min Range: -4.3472

Max Act: 3.0861. Min Act: -0.0000

Data Index: 1090078 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 4.3472. Min Range: -4.3472

Max Act: 3.0881. Min Act: -0.0000

Data Index: 609942 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.9813. Min Act: -0.0001

Data Index: 217117 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.9435. Min Act: -0.0001

Data Index: 476175 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.1457. Min Act: -0.0001

Data Index: 834765 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.4364. Min Act: -0.0000

Data Index: 870051 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.6738. Min Act: -0.0001

Data Index: 116368 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.6040. Min Act: -0.0000

Data Index: 97856 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.0713. Min Act: -0.0000

Data Index: 729469 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.0408. Min Act: -0.0000

Data Index: 437175 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.2398. Min Act: -0.0000

Data Index: 20622 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.1881. Min Act: -0.0001

Data Index: 21192 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.0653. Min Act: -0.0001

Data Index: 965896 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 4.3472. Min Range: -4.3472

Max Act: 1.9108. Min Act: -0.0001

Data Index: 734531 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 4.3472. Min Range: -4.3472

Max Act: 1.5511. Min Act: -0.0000

Data Index: 878608 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.0202. Min Act: -0.0001

Data Index: 744932 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.0991. Min Act: -0.0001

Data Index: 388563 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.0770. Min Act: -0.0000

Data Index: 897990 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 4.3472. Min Range: -4.3472

Max Act: 2.0429. Min Act: -0.0001

Data Index: 419308 (C4 (Web Text))

Max Activating Token Index: 573