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

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

Neuron 700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.5155. Min Act: -0.0000

Data Index: 110899 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.4868. Min Act: -0.0001

Data Index: 984341 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.3959. Min Act: -0.0000

Data Index: 852632 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.4917. Min Act: -0.0001

Data Index: 936688 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.4292. Min Act: -0.0001

Data Index: 1282347 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.4178. Min Act: -0.0001

Data Index: 176629 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.4396. Min Act: -0.0001

Data Index: 637910 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.3969. Min Act: -0.0001

Data Index: 1275042 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.3978. Min Act: -0.0000

Data Index: 509600 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.4706. Min Act: -0.0001

Data Index: 933835 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.3644. Min Act: -0.0000

Data Index: 649927 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.3212. Min Act: -0.0001

Data Index: 881930 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1205755 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.4152. Min Act: -0.0001

Data Index: 1104308 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.3235. Min Act: -0.0001

Data Index: 445730 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.1144. Min Act: -0.0001

Data Index: 1131636 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.2493. Min Act: -0.0000

Data Index: 510368 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.2643. Min Act: -0.0001

Data Index: 967758 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1097588 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.5155. Min Range: -1.5155

Max Act: 1.2737. Min Act: -0.0001

Data Index: 902813 (C4 (Web Text))

Max Activating Token Index: 96