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

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

Neuron 2628 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.2771. Min Act: -0.0000

Data Index: 363254 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.1085. Min Act: -0.0000

Data Index: 224810 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0749. Min Act: -0.0000

Data Index: 202702 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0138. Min Act: -0.0000

Data Index: 242902 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0385. Min Act: -0.0000

Data Index: 11410 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1524845 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9513. Min Act: -0.0000

Data Index: 243237 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1431249 (Python Code)

Max Activating Token Index: 735

Text #8

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9503. Min Act: -0.0000

Data Index: 573990 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9566. Min Act: -0.0000

Data Index: 686194 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1204872 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9775. Min Act: -0.0000

Data Index: 310665 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1297198 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9020. Min Act: -0.0000

Data Index: 4412 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9564. Min Act: -0.0000

Data Index: 195215 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.8750. Min Act: -0.0000

Data Index: 113351 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9511. Min Act: -0.0000

Data Index: 832869 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1260779 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9519. Min Act: -0.0000

Data Index: 339629 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1115065 (C4 (Web Text))

Max Activating Token Index: 680