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

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

Neuron 4153 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2142. Min Range: -3.2142

Max Act: 3.2142. Min Act: -0.0000

Data Index: 406390 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 3.2142. Min Range: -3.2142

Max Act: 2.5810. Min Act: -0.0000

Data Index: 456686 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 3.2142. Min Range: -3.2142

Max Act: 2.1959. Min Act: -0.0000

Data Index: 601562 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 3.2142. Min Range: -3.2142

Max Act: 2.1326. Min Act: -0.0000

Data Index: 688301 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 3.2142. Min Range: -3.2142

Max Act: 2.1840. Min Act: -0.0000

Data Index: 1190693 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 3.2142. Min Range: -3.2142

Max Act: 2.0696. Min Act: -0.0000

Data Index: 833868 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 3.2142. Min Range: -3.2142

Max Act: 2.0535. Min Act: -0.0000

Data Index: 268100 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.9825. Min Act: -0.0000

Data Index: 1125106 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 3.2142. Min Range: -3.2142

Max Act: 2.0412. Min Act: -0.0000

Data Index: 13467 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.8995. Min Act: -0.0000

Data Index: 1026511 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.8685. Min Act: -0.0000

Data Index: 349427 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.7773. Min Act: -0.0000

Data Index: 1220075 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.7829. Min Act: -0.0000

Data Index: 1104701 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.9321. Min Act: -0.0000

Data Index: 1039887 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.6815. Min Act: -0.0000

Data Index: 721344 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.7691. Min Act: -0.0000

Data Index: 504311 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.6301. Min Act: -0.0000

Data Index: 5750 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.7187. Min Act: -0.0000

Data Index: 455890 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.6297. Min Act: -0.0000

Data Index: 908021 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 3.2142. Min Range: -3.2142

Max Act: 1.6933. Min Act: -0.0000

Data Index: 465867 (C4 (Web Text))

Max Activating Token Index: 473