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

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

Neuron 5090 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0613. Min Act: 0.0000

Data Index: 307631 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0301. Min Act: -0.0000

Data Index: 687738 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9586. Min Act: -0.0000

Data Index: 49078 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9202. Min Act: -0.0000

Data Index: 324030 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9166. Min Act: -0.0000

Data Index: 538528 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1289564 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9052. Min Act: -0.0000

Data Index: 391909 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1217511 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8918. Min Act: -0.0000

Data Index: 936708 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8823. Min Act: 0.0000

Data Index: 76255 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8806. Min Act: -0.0000

Data Index: 626259 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8717. Min Act: -0.0000

Data Index: 936366 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9210. Min Act: -0.0000

Data Index: 969504 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8577. Min Act: -0.0000

Data Index: 862458 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8564. Min Act: -0.0000

Data Index: 765997 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8336. Min Act: -0.0000

Data Index: 125811 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8257. Min Act: -0.0000

Data Index: 751422 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8241. Min Act: -0.0000

Data Index: 853011 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8179. Min Act: -0.0000

Data Index: 596122 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1029052 (C4 (Web Text))

Max Activating Token Index: 808