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

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

Neuron 1630 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.5950. Min Act: -0.0001

Data Index: 384898 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.5799. Min Act: -0.0001

Data Index: 477243 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.4464. Min Act: -0.0001

Data Index: 699113 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.3575. Min Act: -0.0001

Data Index: 235929 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.4413. Min Act: -0.0001

Data Index: 312121 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.3942. Min Act: -0.0001

Data Index: 799955 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1262625 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2224. Min Act: -0.0001

Data Index: 860667 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2648. Min Act: -0.0001

Data Index: 1146692 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2869. Min Act: -0.0001

Data Index: 46768 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2849. Min Act: -0.0001

Data Index: 817884 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.3144. Min Act: -0.0001

Data Index: 444876 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2282. Min Act: -0.0001

Data Index: 575841 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.3052. Min Act: -0.0001

Data Index: 1066983 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2221. Min Act: -0.0001

Data Index: 417888 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2544. Min Act: -0.0001

Data Index: 837387 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.1803. Min Act: -0.0001

Data Index: 1072056 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.1985. Min Act: -0.0001

Data Index: 86505 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2453. Min Act: -0.0001

Data Index: 1165530 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 1.5950. Min Range: -1.5950

Max Act: 1.2279. Min Act: -0.0001

Data Index: 1259006 (C4 (Web Text))

Max Activating Token Index: 641