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

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

Neuron 1931 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: 0.9122. Min Range: -0.9122

Max Act: 0.9122. Min Act: -0.0002

Data Index: 990100 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.8274. Min Act: -0.0001

Data Index: 1241890 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.8487. Min Act: -0.0002

Data Index: 894977 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.8266. Min Act: -0.0001

Data Index: 328386 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7761. Min Act: -0.0002

Data Index: 1052127 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7773. Min Act: -0.0001

Data Index: 799293 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.8122. Min Act: -0.0002

Data Index: 648622 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7745. Min Act: -0.0002

Data Index: 329837 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7873. Min Act: -0.0001

Data Index: 1194979 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7442. Min Act: -0.0001

Data Index: 550599 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7450. Min Act: -0.0002

Data Index: 130889 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7314. Min Act: -0.0002

Data Index: 634766 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.6073. Min Act: -0.0001

Data Index: 1019279 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7211. Min Act: -0.0001

Data Index: 409755 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.6816. Min Act: -0.0002

Data Index: 652710 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7234. Min Act: -0.0001

Data Index: 1239063 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.6755. Min Act: -0.0001

Data Index: 108326 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.6991. Min Act: -0.0002

Data Index: 771978 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.7403. Min Act: -0.0001

Data Index: 935692 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.9122. Min Range: -0.9122

Max Act: 0.6960. Min Act: -0.0002

Data Index: 688452 (C4 (Web Text))

Max Activating Token Index: 792