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

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

Neuron 658 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: 2.7054. Min Range: -2.7054

Max Act: 2.7054. Min Act: -0.0000

Data Index: 588771 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.6302. Min Act: -0.0000

Data Index: 925467 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.4930. Min Act: -0.0000

Data Index: 522387 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.4930. Min Act: -0.0000

Data Index: 1142582 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.6100. Min Act: -0.0000

Data Index: 1015465 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.4678. Min Act: -0.0001

Data Index: 137851 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.2875. Min Act: -0.0000

Data Index: 1225495 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.4767. Min Act: -0.0000

Data Index: 34593 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.2397. Min Act: -0.0000

Data Index: 733080 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.3433. Min Act: -0.0000

Data Index: 1352375 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.6493. Min Act: -0.0000

Data Index: 1288087 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.3951. Min Act: -0.0000

Data Index: 466494 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.2315. Min Act: -0.0000

Data Index: 1002634 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.4230. Min Act: -0.0000

Data Index: 568409 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.1390. Min Act: -0.0000

Data Index: 1065475 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.0974. Min Act: -0.0000

Data Index: 1154782 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.1135. Min Act: -0.0000

Data Index: 701879 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.0966. Min Act: -0.0000

Data Index: 702967 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.1871. Min Act: -0.0001

Data Index: 879861 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.0848. Min Act: -0.0000

Data Index: 806037 (C4 (Web Text))

Max Activating Token Index: 46