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

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

Neuron 3009 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: 0.7050. Min Range: -0.7050

Max Act: 0.6917. Min Act: -0.0002

Data Index: 660766 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.7050. Min Act: -0.0001

Data Index: 1572246 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.7017. Min Act: -0.0002

Data Index: 3777 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6784. Min Act: -0.0001

Data Index: 1139545 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6516. Min Act: -0.0001

Data Index: 1397400 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6911. Min Act: -0.0001

Data Index: 1280397 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6212. Min Act: -0.0002

Data Index: 1022298 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6179. Min Act: -0.0001

Data Index: 1539064 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5993. Min Act: -0.0002

Data Index: 75944 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6192. Min Act: -0.0002

Data Index: 568350 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6235. Min Act: -0.0002

Data Index: 1100234 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6131. Min Act: -0.0002

Data Index: 502830 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6288. Min Act: -0.0001

Data Index: 1627324 (Python Code)

Max Activating Token Index: 974

Text #13

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6485. Min Act: -0.0001

Data Index: 1488276 (Python Code)

Max Activating Token Index: 995

Text #14

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5847. Min Act: -0.0002

Data Index: 931170 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5829. Min Act: -0.0001

Data Index: 342059 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6154. Min Act: -0.0002

Data Index: 1344552 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6201. Min Act: -0.0002

Data Index: 952014 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6000. Min Act: -0.0002

Data Index: 1137610 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5944. Min Act: -0.0001

Data Index: 585049 (C4 (Web Text))

Max Activating Token Index: 99