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

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

Neuron 2457 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: 1.1569. Min Range: -1.1569

Max Act: 1.1569. Min Act: -0.0000

Data Index: 599243 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0755. Min Act: -0.0000

Data Index: 652667 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0773. Min Act: -0.0000

Data Index: 314 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0675. Min Act: -0.0000

Data Index: 839655 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0158. Min Act: -0.0000

Data Index: 473285 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1051030 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9353. Min Act: -0.0000

Data Index: 240777 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0690. Min Act: -0.0000

Data Index: 406019 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9642. Min Act: -0.0000

Data Index: 390874 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9408. Min Act: -0.0000

Data Index: 370902 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0092. Min Act: -0.0000

Data Index: 202033 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1208936 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9299. Min Act: -0.0000

Data Index: 609812 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1267600 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1314359 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9313. Min Act: -0.0000

Data Index: 73500 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9990. Min Act: -0.0000

Data Index: 847075 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9357. Min Act: -0.0000

Data Index: 771981 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.8835. Min Act: -0.0000

Data Index: 196079 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1008675 (C4 (Web Text))

Max Activating Token Index: 71