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

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

Neuron 4194 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: 2.2783. Min Range: -2.2783

Max Act: 2.2783. Min Act: -0.0000

Data Index: 753183 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.2783. Min Range: -2.2783

Max Act: 2.1288. Min Act: 0.0000

Data Index: 44844 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.2783. Min Range: -2.2783

Max Act: 2.0267. Min Act: -0.0000

Data Index: 737894 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 2.2783. Min Range: -2.2783

Max Act: 2.0099. Min Act: -0.0000

Data Index: 855636 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 2.2783. Min Range: -2.2783

Max Act: 2.0759. Min Act: -0.0000

Data Index: 389005 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 2.2783. Min Range: -2.2783

Max Act: 2.0665. Min Act: -0.0000

Data Index: 765064 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.9423. Min Act: -0.0000

Data Index: 151876 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.9365. Min Act: -0.0000

Data Index: 1355405 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.9056. Min Act: -0.0000

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.9234. Min Act: -0.0000

Data Index: 44363 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.9645. Min Act: -0.0000

Data Index: 474646 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.8184. Min Act: -0.0000

Data Index: 342091 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.8012. Min Act: -0.0000

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.7513. Min Act: -0.0000

Data Index: 118251 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.8449. Min Act: -0.0000

Data Index: 334750 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.7330. Min Act: -0.0000

Data Index: 294378 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.8277. Min Act: -0.0000

Data Index: 54092 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.7209. Min Act: -0.0000

Data Index: 188949 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.7115. Min Act: 0.0000

Data Index: 723977 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 2.2783. Min Range: -2.2783

Max Act: 1.6989. Min Act: -0.0000

Data Index: 240281 (C4 (Web Text))

Max Activating Token Index: 44