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

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

Neuron 2221 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.8972. Min Act: -0.0000

Data Index: 1158887 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.6923. Min Act: -0.0001

Data Index: 1340409 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.7621. Min Act: -0.0001

Data Index: 1293256 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.7284. Min Act: -0.0000

Data Index: 215660 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.7140. Min Act: -0.0000

Data Index: 618984 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.5935. Min Act: -0.0000

Data Index: 735399 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.5578. Min Act: -0.0000

Data Index: 510860 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.6254. Min Act: -0.0000

Data Index: 200065 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.6251. Min Act: -0.0000

Data Index: 93171 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.4663. Min Act: -0.0000

Data Index: 286911 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.5341. Min Act: -0.0000

Data Index: 666901 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.5216. Min Act: -0.0001

Data Index: 424352 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.7199. Min Act: -0.0000

Data Index: 1117020 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.5226. Min Act: -0.0000

Data Index: 304232 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.5808. Min Act: -0.0000

Data Index: 1351849 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.5050. Min Act: -0.0000

Data Index: 484733 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.4948. Min Act: -0.0000

Data Index: 731911 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.4813. Min Act: -0.0001

Data Index: 815533 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1308373 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.8972. Min Range: -1.8972

Max Act: 1.4559. Min Act: -0.0001

Data Index: 128934 (C4 (Web Text))

Max Activating Token Index: 46