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

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

Neuron 1152 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6842. Min Act: -0.0000

Data Index: 874352 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.1903. Min Act: -0.0001

Data Index: 149525 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.3613. Min Act: -0.0001

Data Index: 265597 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.3014. Min Act: -0.0000

Data Index: 542670 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.2401. Min Act: -0.0001

Data Index: 1322595 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.2806. Min Act: -0.0000

Data Index: 413297 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.1372. Min Act: -0.0001

Data Index: 851463 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1078235 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.1902. Min Act: -0.0001

Data Index: 265890 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.1484. Min Act: -0.0001

Data Index: 719546 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.0584. Min Act: -0.0001

Data Index: 977585 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.9714. Min Act: -0.0001

Data Index: 220167 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.1158. Min Act: -0.0001

Data Index: 48354 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.1065. Min Act: -0.0001

Data Index: 699575 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.0150. Min Act: -0.0001

Data Index: 934482 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.0436. Min Act: -0.0000

Data Index: 886399 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.1027. Min Act: -0.0001

Data Index: 1085921 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.0059. Min Act: -0.0001

Data Index: 841835 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1252408 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.9909. Min Act: -0.0000

Data Index: 36217 (C4 (Web Text))

Max Activating Token Index: 138