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

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

Neuron 1754 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7440. Min Range: -2.7440

Max Act: 2.7440. Min Act: -0.0000

Data Index: 997989 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 2.7440. Min Range: -2.7440

Max Act: 2.1915. Min Act: -0.0000

Data Index: 527353 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 2.7440. Min Range: -2.7440

Max Act: 2.2508. Min Act: -0.0000

Data Index: 505876 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.9719. Min Act: -0.0000

Data Index: 650479 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.9773. Min Act: -0.0000

Data Index: 405379 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.8486. Min Act: -0.0000

Data Index: 743896 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.8260. Min Act: -0.0000

Data Index: 226232 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.6321. Min Act: -0.0000

Data Index: 711220 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1474417 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.5190. Min Act: -0.0000

Data Index: 950405 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.4244. Min Act: -0.0000

Data Index: 13342 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.2860. Min Act: -0.0000

Data Index: 453515 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.3827. Min Act: -0.0000

Data Index: 619254 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1229353 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1267371 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.4472. Min Act: -0.0000

Data Index: 998629 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.3544. Min Act: -0.0000

Data Index: 1328433 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.4294. Min Act: -0.0000

Data Index: 1396108 (Python Code)

Max Activating Token Index: 108

Text #18

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.4859. Min Act: -0.0000

Data Index: 768604 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 2.7440. Min Range: -2.7440

Max Act: 1.4229. Min Act: -0.0000

Data Index: 660223 (C4 (Web Text))

Max Activating Token Index: 310