Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1696. Min Range: -3.1696

Max Act: 3.1696. Min Act: -0.0002

Data Index: 1232826 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.7009. Min Act: -0.0002

Data Index: 638768 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.4674. Min Act: -0.0002

Data Index: 1200097 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.4496. Min Act: -0.0002

Data Index: 1071090 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.6052. Min Act: -0.0002

Data Index: 295109 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.4549. Min Act: -0.0001

Data Index: 1585509 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.4027. Min Act: -0.0001

Data Index: 493241 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.5199. Min Act: -0.0002

Data Index: 1068325 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.3894. Min Act: -0.0001

Data Index: 1033658 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.6317. Min Act: -0.0002

Data Index: 778942 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.3423. Min Act: -0.0002

Data Index: 1262517 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.2218. Min Act: -0.0001

Data Index: 1399848 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.3226. Min Act: -0.0001

Data Index: 526169 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.4058. Min Act: -0.0002

Data Index: 150697 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.3752. Min Act: -0.0002

Data Index: 761840 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.2589. Min Act: -0.0001

Data Index: 597627 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.3792. Min Act: -0.0001

Data Index: 241999 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.2542. Min Act: -0.0002

Data Index: 484902 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.2414. Min Act: -0.0002

Data Index: 1042966 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 3.1696. Min Range: -3.1696

Max Act: 2.1222. Min Act: -0.0001

Data Index: 324693 (C4 (Web Text))

Max Activating Token Index: 314