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

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

Neuron 4302 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1277954 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.8378. Min Act: -0.0000

Data Index: 84595 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.9066. Min Act: -0.0000

Data Index: 999722 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.9196. Min Act: -0.0000

Data Index: 254000 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.8861. Min Act: -0.0000

Data Index: 305922 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1291290 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7743. Min Act: -0.0000

Data Index: 661020 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.8258. Min Act: -0.0000

Data Index: 572749 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1302544 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7471. Min Act: -0.0000

Data Index: 706896 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7556. Min Act: -0.0000

Data Index: 980409 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1158681 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.6959. Min Act: -0.0000

Data Index: 262802 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7761. Min Act: -0.0000

Data Index: 182347 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1350340 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1072021 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7123. Min Act: -0.0000

Data Index: 567079 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7379. Min Act: -0.0000

Data Index: 425529 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.6986. Min Act: -0.0000

Data Index: 661102 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.9722. Min Range: -0.9722

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1216383 (C4 (Web Text))

Max Activating Token Index: 267