Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1883 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.6596. Min Act: -0.0000

Data Index: 1001289 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1059263 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.1862. Min Act: -0.0000

Data Index: 674686 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.3135. Min Act: -0.0000

Data Index: 213268 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.3021. Min Act: -0.0000

Data Index: 1189912 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1106962 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.1458. Min Act: -0.0000

Data Index: 853798 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.0266. Min Act: -0.0000

Data Index: 218660 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.1158. Min Act: -0.0000

Data Index: 196592 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.0380. Min Act: -0.0000

Data Index: 591282 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.0108. Min Act: -0.0000

Data Index: 186296 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1153719 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1145943 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9421. Min Act: -0.0000

Data Index: 630941 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 1.6596. Min Range: -1.6596

Max Act: 1.0563. Min Act: -0.0000

Data Index: 338402 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9869. Min Act: -0.0000

Data Index: 690857 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1050164 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9817. Min Act: -0.0000

Data Index: 687013 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9759. Min Act: -0.0000

Data Index: 111863 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.6596. Min Range: -1.6596

Max Act: 0.9624. Min Act: -0.0000

Data Index: 522075 (C4 (Web Text))

Max Activating Token Index: 928