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

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

Neuron 541 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2542. Min Act: -0.0001

Data Index: 19126 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1258813 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2502. Min Act: -0.0000

Data Index: 278205 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2153. Min Act: -0.0000

Data Index: 798118 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1100415 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2224. Min Act: -0.0000

Data Index: 28217 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2063. Min Act: -0.0000

Data Index: 312459 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2012. Min Act: -0.0001

Data Index: 776938 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2079. Min Act: -0.0000

Data Index: 304449 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1311692 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2269. Min Act: -0.0000

Data Index: 23468 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1949. Min Act: -0.0000

Data Index: 333888 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2271. Min Act: -0.0001

Data Index: 256547 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1833. Min Act: -0.0000

Data Index: 220226 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1975. Min Act: -0.0000

Data Index: 480419 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1980. Min Act: -0.0001

Data Index: 271251 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1237397 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1338386 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1188899 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1093691 (C4 (Web Text))

Max Activating Token Index: 559