Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2770 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2318. Min Act: -0.0001

Data Index: 161418 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2205. Min Act: -0.0001

Data Index: 787163 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2040. Min Act: -0.0001

Data Index: 16090 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2120. Min Act: -0.0001

Data Index: 487712 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2075. Min Act: -0.0001

Data Index: 602059 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1954. Min Act: 0.0001

Data Index: 817259 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1850. Min Act: -0.0001

Data Index: 470125 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1912. Min Act: -0.0001

Data Index: 438819 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1779. Min Act: -0.0001

Data Index: 434416 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1247773 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1934. Min Act: -0.0001

Data Index: 998227 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1861. Min Act: -0.0000

Data Index: 458439 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1832. Min Act: -0.0001

Data Index: 231785 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1876. Min Act: -0.0001

Data Index: 497120 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1279253 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1879. Min Act: -0.0001

Data Index: 604374 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1206935 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1861. Min Act: -0.0001

Data Index: 578054 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1345018 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1786. Min Act: -0.0001

Data Index: 182645 (C4 (Web Text))

Max Activating Token Index: 950