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

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

Neuron 504 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.8157. Min Act: -0.0001

Data Index: 1148056 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6213. Min Act: -0.0001

Data Index: 1234979 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6627. Min Act: -0.0001

Data Index: 1321751 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6128. Min Act: -0.0001

Data Index: 201226 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6311. Min Act: -0.0001

Data Index: 1205095 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6851. Min Act: -0.0001

Data Index: 507640 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6085. Min Act: -0.0001

Data Index: 556192 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6170. Min Act: -0.0001

Data Index: 938719 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6058. Min Act: -0.0001

Data Index: 778300 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5851. Min Act: -0.0001

Data Index: 431012 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6083. Min Act: -0.0001

Data Index: 880831 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5866. Min Act: -0.0001

Data Index: 405766 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5782. Min Act: -0.0001

Data Index: 501094 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5625. Min Act: -0.0001

Data Index: 1346577 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5775. Min Act: -0.0001

Data Index: 1127989 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5593. Min Act: -0.0001

Data Index: 269173 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5778. Min Act: -0.0001

Data Index: 967612 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5938. Min Act: -0.0001

Data Index: 109536 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5557. Min Act: -0.0001

Data Index: 560894 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6030. Min Act: -0.0001

Data Index: 870621 (C4 (Web Text))

Max Activating Token Index: 547