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

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

Neuron 4413 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.6431. Min Act: -0.0001

Data Index: 268339 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.6756. Min Act: -0.0001

Data Index: 11231 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5839. Min Act: -0.0001

Data Index: 420745 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.6248. Min Act: -0.0001

Data Index: 121284 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4678. Min Act: -0.0001

Data Index: 984200 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5708. Min Act: -0.0001

Data Index: 1163745 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.6181. Min Act: -0.0001

Data Index: 714638 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5544. Min Act: -0.0001

Data Index: 1212119 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5572. Min Act: -0.0001

Data Index: 28412 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5554. Min Act: -0.0001

Data Index: 325500 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4789. Min Act: -0.0001

Data Index: 360015 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4660. Min Act: -0.0001

Data Index: 677411 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5094. Min Act: -0.0001

Data Index: 476738 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4876. Min Act: -0.0001

Data Index: 911123 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4600. Min Act: -0.0001

Data Index: 539442 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5329. Min Act: -0.0001

Data Index: 344056 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5303. Min Act: -0.0001

Data Index: 152174 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5299. Min Act: -0.0001

Data Index: 274756 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4772. Min Act: -0.0001

Data Index: 286092 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4584. Min Act: -0.0001

Data Index: 517444 (C4 (Web Text))

Max Activating Token Index: 109