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

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

Neuron 317 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.7453. Min Act: -0.0001

Data Index: 933796 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4527. Min Act: -0.0001

Data Index: 757030 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4329. Min Act: -0.0001

Data Index: 1335757 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3288. Min Act: -0.0001

Data Index: 210461 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2951. Min Act: -0.0001

Data Index: 864604 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3274. Min Act: -0.0001

Data Index: 838312 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3503. Min Act: -0.0001

Data Index: 507450 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2363. Min Act: -0.0001

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2339. Min Act: -0.0001

Data Index: 1259608 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2912. Min Act: -0.0001

Data Index: 1083401 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.1756. Min Act: -0.0001

Data Index: 863207 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2448. Min Act: -0.0001

Data Index: 1054276 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.1258. Min Act: -0.0001

Data Index: 859095 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.1585. Min Act: -0.0001

Data Index: 642041 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.1829. Min Act: -0.0001

Data Index: 498206 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.1341. Min Act: -0.0001

Data Index: 371320 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2275. Min Act: -0.0001

Data Index: 609779 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.1520. Min Act: -0.0001

Data Index: 236063 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.1094. Min Act: -0.0001

Data Index: 324274 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.0758. Min Act: -0.0001

Data Index: 602660 (C4 (Web Text))

Max Activating Token Index: 144