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

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

Neuron 3575 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3708. Min Act: -0.0000

Data Index: 184673 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3750. Min Act: -0.0000

Data Index: 345006 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3533. Min Act: -0.0000

Data Index: 612325 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3509. Min Act: -0.0000

Data Index: 507098 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3372. Min Act: -0.0000

Data Index: 561123 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3463. Min Act: -0.0000

Data Index: 404514 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3482. Min Act: -0.0000

Data Index: 824300 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3514. Min Act: -0.0000

Data Index: 742696 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1347534 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3231. Min Act: -0.0000

Data Index: 325709 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3307. Min Act: -0.0000

Data Index: 347030 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1302482 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3221. Min Act: -0.0000

Data Index: 759436 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2851. Min Act: -0.0000

Data Index: 973219 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3121. Min Act: -0.0000

Data Index: 737367 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3055. Min Act: -0.0000

Data Index: 532574 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3063. Min Act: -0.0000

Data Index: 155714 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1165607 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1210022 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.3750. Min Range: -0.3750

Max Act: 0.3068. Min Act: -0.0000

Data Index: 51791 (C4 (Web Text))

Max Activating Token Index: 140