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

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

Neuron 2333 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: 2.6406. Min Range: -2.6406

Max Act: 2.5240. Min Act: -0.0000

Data Index: 359543 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 2.6406. Min Range: -2.6406

Max Act: 2.6406. Min Act: -0.0000

Data Index: 950576 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 2.6406. Min Range: -2.6406

Max Act: 2.0298. Min Act: -0.0000

Data Index: 810267 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 2.6406. Min Range: -2.6406

Max Act: 2.2038. Min Act: -0.0000

Data Index: 734322 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 2.6406. Min Range: -2.6406

Max Act: 2.1820. Min Act: -0.0000

Data Index: 791196 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 2.6406. Min Range: -2.6406

Max Act: 2.0998. Min Act: -0.0000

Data Index: 1315501 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 2.6406. Min Range: -2.6406

Max Act: 2.0802. Min Act: -0.0000

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.8372. Min Act: -0.0000

Data Index: 596246 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.7220. Min Act: -0.0000

Data Index: 330057 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.7891. Min Act: -0.0000

Data Index: 389378 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1101808 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.6412. Min Act: -0.0000

Data Index: 635078 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.6727. Min Act: -0.0000

Data Index: 810879 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.6484. Min Act: -0.0000

Data Index: 147985 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.5424. Min Act: -0.0000

Data Index: 1358679 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.5875. Min Act: -0.0000

Data Index: 340220 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.3953. Min Act: -0.0000

Data Index: 138183 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.5527. Min Act: -0.0000

Data Index: 1173799 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.4949. Min Act: -0.0000

Data Index: 1534928 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.6406. Min Range: -2.6406

Max Act: 1.5619. Min Act: -0.0000

Data Index: 199395 (C4 (Web Text))

Max Activating Token Index: 879