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

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

Neuron 5162 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2569. Min Act: -0.0000

Data Index: 507337 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1267484 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2412. Min Act: -0.0000

Data Index: 877234 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1081705 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2138. Min Act: -0.0000

Data Index: 629140 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2128. Min Act: -0.0000

Data Index: 784296 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2054. Min Act: -0.0000

Data Index: 50633 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2044. Min Act: 0.0000

Data Index: 605236 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1779. Min Act: -0.0000

Data Index: 24190 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1841. Min Act: -0.0000

Data Index: 696268 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1813. Min Act: -0.0000

Data Index: 948868 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1817. Min Act: -0.0000

Data Index: 827584 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1709. Min Act: -0.0000

Data Index: 791188 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1712. Min Act: -0.0000

Data Index: 94764 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1695. Min Act: -0.0000

Data Index: 796707 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1726. Min Act: -0.0000

Data Index: 938729 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1752. Min Act: -0.0000

Data Index: 844066 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1646. Min Act: -0.0000

Data Index: 992487 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1685. Min Act: -0.0000

Data Index: 919829 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1252906 (C4 (Web Text))

Max Activating Token Index: 534