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

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

Neuron 3366 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.8823. Min Act: -0.0000

Data Index: 2241 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5889. Min Act: -0.0000

Data Index: 1052377 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.6241. Min Act: -0.0000

Data Index: 1184189 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5507. Min Act: -0.0000

Data Index: 670377 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5040. Min Act: -0.0000

Data Index: 337992 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4248. Min Act: -0.0000

Data Index: 584649 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4859. Min Act: -0.0000

Data Index: 374064 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4748. Min Act: -0.0000

Data Index: 938213 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.2300. Min Act: -0.0000

Data Index: 372831 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4726. Min Act: -0.0000

Data Index: 305992 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4514. Min Act: -0.0000

Data Index: 1150132 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3988. Min Act: -0.0000

Data Index: 288236 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3075. Min Act: -0.0000

Data Index: 747934 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3767. Min Act: -0.0000

Data Index: 181985 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3409. Min Act: -0.0000

Data Index: 432001 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.2504. Min Act: -0.0000

Data Index: 537975 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.2992. Min Act: -0.0000

Data Index: 384572 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1010160 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.2271. Min Act: -0.0000

Data Index: 511023 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4402. Min Act: -0.0000

Data Index: 811785 (C4 (Web Text))

Max Activating Token Index: 767