Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3720 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1418. Min Range: -4.1418

Max Act: 4.1418. Min Act: -0.0000

Data Index: 555529 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 4.1418. Min Range: -4.1418

Max Act: 3.7185. Min Act: -0.0000

Data Index: 884279 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 4.1418. Min Range: -4.1418

Max Act: 3.4987. Min Act: -0.0000

Data Index: 119255 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 4.1418. Min Range: -4.1418

Max Act: 3.0783. Min Act: -0.0000

Data Index: 174334 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.7951. Min Act: -0.0000

Data Index: 9603 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.8776. Min Act: -0.0000

Data Index: 12457 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.9982. Min Act: -0.0000

Data Index: 671690 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.8657. Min Act: -0.0000

Data Index: 1102445 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.9656. Min Act: -0.0000

Data Index: 1173599 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.6935. Min Act: -0.0000

Data Index: 577326 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.3894. Min Act: -0.0000

Data Index: 1187316 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.4801. Min Act: -0.0000

Data Index: 1589001 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.6321. Min Act: -0.0000

Data Index: 869584 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.6071. Min Act: -0.0000

Data Index: 1040692 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.7269. Min Act: -0.0000

Data Index: 968748 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.5620. Min Act: -0.0000

Data Index: 346212 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.5507. Min Act: -0.0000

Data Index: 79947 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.5269. Min Act: -0.0000

Data Index: 1276085 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.5319. Min Act: -0.0000

Data Index: 769395 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 4.1418. Min Range: -4.1418

Max Act: 2.4607. Min Act: -0.0000

Data Index: 481663 (C4 (Web Text))

Max Activating Token Index: 13