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

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

Neuron 2589 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.8183. Min Act: -0.0001

Data Index: 851044 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1253660 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1201186 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.7055. Min Act: -0.0000

Data Index: 37807 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6583. Min Act: -0.0001

Data Index: 510664 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.7162. Min Act: -0.0001

Data Index: 254754 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1139877 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.7136. Min Act: -0.0001

Data Index: 134804 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6642. Min Act: -0.0000

Data Index: 857268 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6447. Min Act: -0.0001

Data Index: 255783 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6350. Min Act: -0.0000

Data Index: 851519 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6353. Min Act: -0.0000

Data Index: 320593 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.5886. Min Act: -0.0001

Data Index: 993079 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6641. Min Act: -0.0000

Data Index: 402355 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6606. Min Act: -0.0001

Data Index: 702229 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6580. Min Act: -0.0001

Data Index: 898010 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6190. Min Act: -0.0001

Data Index: 227621 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1052803 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6152. Min Act: -0.0001

Data Index: 313882 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.8183. Min Range: -0.8183

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1238432 (C4 (Web Text))

Max Activating Token Index: 601