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

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

Neuron 2308 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: 1.4898. Min Range: -1.4898

Max Act: 1.4898. Min Act: -0.0001

Data Index: 1182330 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.1295. Min Act: -0.0001

Data Index: 1060926 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.3076. Min Act: -0.0001

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.1700. Min Act: -0.0001

Data Index: 9223 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.1466. Min Act: -0.0001

Data Index: 367276 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.1074. Min Act: -0.0001

Data Index: 1026602 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0801. Min Act: -0.0001

Data Index: 1344004 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0098. Min Act: -0.0001

Data Index: 791165 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0107. Min Act: -0.0001

Data Index: 1340708 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0116. Min Act: -0.0001

Data Index: 333152 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.4898. Min Range: -1.4898

Max Act: 1.0235. Min Act: -0.0001

Data Index: 466840 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9294. Min Act: -0.0001

Data Index: 251314 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9519. Min Act: -0.0001

Data Index: 433713 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9485. Min Act: -0.0002

Data Index: 20072 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.8627. Min Act: -0.0001

Data Index: 601363 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9999. Min Act: -0.0001

Data Index: 684968 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.8806. Min Act: -0.0001

Data Index: 760089 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9016. Min Act: -0.0001

Data Index: 1189749 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.8798. Min Act: -0.0001

Data Index: 541538 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.4898. Min Range: -1.4898

Max Act: 0.9016. Min Act: -0.0001

Data Index: 203328 (C4 (Web Text))

Max Activating Token Index: 282