Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 465 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2294. Min Act: -0.0001

Data Index: 1257341 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2929. Min Act: -0.0001

Data Index: 1133848 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1440. Min Act: -0.0001

Data Index: 1211047 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1366. Min Act: -0.0001

Data Index: 1354510 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1203. Min Act: -0.0001

Data Index: 341543 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0792. Min Act: -0.0001

Data Index: 828335 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1019. Min Act: -0.0001

Data Index: 584594 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1542. Min Act: -0.0001

Data Index: 45883 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1010. Min Act: -0.0001

Data Index: 586417 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0081. Min Act: -0.0001

Data Index: 540311 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0324. Min Act: -0.0001

Data Index: 1171814 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0233. Min Act: -0.0001

Data Index: 844919 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0415. Min Act: -0.0001

Data Index: 664612 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0220. Min Act: -0.0001

Data Index: 92542 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0760. Min Act: -0.0001

Data Index: 165488 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.2929. Min Range: -1.2929

Max Act: 0.9801. Min Act: -0.0001

Data Index: 1028118 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0008. Min Act: -0.0001

Data Index: 298540 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.2929. Min Range: -1.2929

Max Act: 0.9745. Min Act: -0.0001

Data Index: 153776 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.2929. Min Range: -1.2929

Max Act: 0.9771. Min Act: -0.0001

Data Index: 640987 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.0015. Min Act: -0.0001

Data Index: 1331298 (C4 (Web Text))

Max Activating Token Index: 920