Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 870 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.5469. Min Act: -0.0002

Data Index: 1114458 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.6066. Min Act: -0.0001

Data Index: 314141 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.5673. Min Act: -0.0002

Data Index: 708696 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.5128. Min Act: -0.0001

Data Index: 835791 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.5048. Min Act: -0.0001

Data Index: 1075468 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.4629. Min Act: -0.0002

Data Index: 587915 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.4353. Min Act: -0.0002

Data Index: 228802 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.4460. Min Act: -0.0002

Data Index: 246213 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.4516. Min Act: -0.0002

Data Index: 865982 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.3519. Min Act: -0.0002

Data Index: 988941 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.4189. Min Act: -0.0002

Data Index: 109578 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.4220. Min Act: -0.0002

Data Index: 1203816 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.3872. Min Act: -0.0001

Data Index: 451322 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.3506. Min Act: -0.0001

Data Index: 393279 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.3767. Min Act: -0.0002

Data Index: 765370 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.3929. Min Act: -0.0001

Data Index: 332005 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.3483. Min Act: -0.0002

Data Index: 615997 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.4233. Min Act: -0.0002

Data Index: 105395 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.4233. Min Act: -0.0002

Data Index: 949956 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 1.6066. Min Range: -1.6066

Max Act: 1.3980. Min Act: -0.0002

Data Index: 614530 (C4 (Web Text))

Max Activating Token Index: 998