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

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

Neuron 1406 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: 2.6280. Min Range: -2.6280

Max Act: 2.6280. Min Act: -0.0000

Data Index: 1445669 (Python Code)

Max Activating Token Index: 414

Text #1

Max Range: 2.6280. Min Range: -2.6280

Max Act: 2.6132. Min Act: -0.0000

Data Index: 1499436 (Python Code)

Max Activating Token Index: 427

Text #2

Max Range: 2.6280. Min Range: -2.6280

Max Act: 2.4195. Min Act: -0.0000

Data Index: 1523933 (Python Code)

Max Activating Token Index: 291

Text #3

Max Range: 2.6280. Min Range: -2.6280

Max Act: 2.4741. Min Act: -0.0001

Data Index: 1508770 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 2.6280. Min Range: -2.6280

Max Act: 2.4355. Min Act: -0.0000

Data Index: 1417892 (Python Code)

Max Activating Token Index: 1002

Text #5

Max Range: 2.6280. Min Range: -2.6280

Max Act: 2.3538. Min Act: -0.0000

Data Index: 1451302 (Python Code)

Max Activating Token Index: 270

Text #6

Max Range: 2.6280. Min Range: -2.6280

Max Act: 2.3306. Min Act: -0.0000

Data Index: 1597300 (Python Code)

Max Activating Token Index: 939

Text #7

Max Range: 2.6280. Min Range: -2.6280

Max Act: 2.0618. Min Act: -0.0000

Data Index: 1544331 (Python Code)

Max Activating Token Index: 42

Text #8

Max Range: 2.6280. Min Range: -2.6280

Max Act: 2.0123. Min Act: -0.0000

Data Index: 26409 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.9322. Min Act: -0.0000

Data Index: 1460496 (Python Code)

Max Activating Token Index: 686

Text #10

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.6701. Min Act: -0.0000

Data Index: 1587625 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.5879. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1553465 (Python Code)

Max Activating Token Index: 873

Text #14

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.4772. Min Act: -0.0000

Data Index: 1555651 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.4670. Min Act: 0.0000

Data Index: 1552373 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1550396 (Python Code)

Max Activating Token Index: 660

Text #17

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.4437. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.3937. Min Act: -0.0000

Data Index: 722864 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 2.6280. Min Range: -2.6280

Max Act: 1.3480. Min Act: -0.0000

Data Index: 663407 (C4 (Web Text))

Max Activating Token Index: 946