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

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

Neuron 3040 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0240. Min Act: -0.0002

Data Index: 648919 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.1682. Min Act: -0.0002

Data Index: 114404 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0676. Min Act: -0.0002

Data Index: 674688 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.1359. Min Act: -0.0002

Data Index: 1131146 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.1682. Min Range: -1.1682

Max Act: 1.0509. Min Act: -0.0002

Data Index: 850193 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9335. Min Act: -0.0002

Data Index: 398985 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9349. Min Act: -0.0002

Data Index: 363106 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8867. Min Act: -0.0002

Data Index: 1193644 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9717. Min Act: -0.0002

Data Index: 1347336 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9907. Min Act: -0.0002

Data Index: 128470 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8794. Min Act: -0.0002

Data Index: 1105608 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8450. Min Act: -0.0002

Data Index: 436535 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8889. Min Act: -0.0002

Data Index: 604868 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.9145. Min Act: -0.0002

Data Index: 1267033 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8793. Min Act: -0.0002

Data Index: 934537 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8507. Min Act: -0.0002

Data Index: 1045196 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8470. Min Act: -0.0002

Data Index: 1018732 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8247. Min Act: -0.0002

Data Index: 813090 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.8431. Min Act: -0.0002

Data Index: 193951 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.1682. Min Range: -1.1682

Max Act: 0.7973. Min Act: -0.0002

Data Index: 1114337 (C4 (Web Text))

Max Activating Token Index: 147