Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 562 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0324. Min Act: -0.0002

Data Index: 206298 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0329. Min Act: -0.0002

Data Index: 155199 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0001

Data Index: 612472 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0326. Min Act: -0.0002

Data Index: 151249 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1183741 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0311. Min Act: -0.0001

Data Index: 409322 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0301. Min Act: -0.0002

Data Index: 651711 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0303. Min Act: -0.0001

Data Index: 465520 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0303. Min Act: -0.0001

Data Index: 669209 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1001408 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1185716 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0304. Min Act: -0.0002

Data Index: 378456 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0281. Min Act: -0.0002

Data Index: 557407 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0286. Min Act: -0.0002

Data Index: 511780 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0275. Min Act: -0.0001

Data Index: 227954 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0284. Min Act: -0.0002

Data Index: 463770 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0288. Min Act: -0.0001

Data Index: 462891 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1252830 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0281. Min Act: -0.0002

Data Index: 854739 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0277. Min Act: -0.0001

Data Index: 403448 (C4 (Web Text))

Max Activating Token Index: 456