Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1040846 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.1729. Min Act: -0.0000

Data Index: 725978 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.0361. Min Act: -0.0001

Data Index: 1142476 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.1515. Min Act: -0.0000

Data Index: 323701 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.1438. Min Act: -0.0000

Data Index: 211724 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.1244. Min Act: -0.0000

Data Index: 850770 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.1044. Min Act: -0.0000

Data Index: 321392 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.0564. Min Act: -0.0000

Data Index: 131309 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1111178 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.0405. Min Act: -0.0001

Data Index: 450818 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1350777 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9709. Min Act: -0.0000

Data Index: 318216 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9200. Min Act: -0.0000

Data Index: 771849 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9418. Min Act: -0.0001

Data Index: 396093 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.0135. Min Act: -0.0000

Data Index: 218912 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8791. Min Act: -0.0001

Data Index: 409551 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1212806 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1104394 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8588. Min Act: -0.0000

Data Index: 78369 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1352145 (C4 (Web Text))

Max Activating Token Index: 163