Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4746 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6677. Min Act: -0.0001

Data Index: 1086405 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6309. Min Act: -0.0001

Data Index: 1336983 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6394. Min Act: -0.0001

Data Index: 518273 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6581. Min Act: -0.0001

Data Index: 420951 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5630. Min Act: -0.0001

Data Index: 36309 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5767. Min Act: -0.0001

Data Index: 20278 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.3888. Min Act: -0.0001

Data Index: 689744 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.6731. Min Act: -0.0001

Data Index: 345303 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.4911. Min Act: -0.0001

Data Index: 1289264 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.4820. Min Act: -0.0001

Data Index: 1009521 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.4678. Min Act: -0.0001

Data Index: 184775 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.4863. Min Act: -0.0001

Data Index: 645456 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.3413. Min Act: -0.0001

Data Index: 1115910 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.5074. Min Act: -0.0001

Data Index: 370085 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.3324. Min Act: -0.0001

Data Index: 1549371 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.4111. Min Act: -0.0001

Data Index: 1159283 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.3364. Min Act: -0.0001

Data Index: 543641 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.3941. Min Act: -0.0001

Data Index: 130778 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.2879. Min Act: -0.0001

Data Index: 1168427 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.6731. Min Range: -1.6731

Max Act: 1.3601. Min Act: -0.0001

Data Index: 503449 (C4 (Web Text))

Max Activating Token Index: 126