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

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

Neuron 1875 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.4678. Min Act: -0.0000

Data Index: 309494 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.5214. Min Act: -0.0000

Data Index: 570624 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.2861. Min Act: -0.0000

Data Index: 482139 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.2496. Min Act: -0.0000

Data Index: 1099820 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1223359 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1079527 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1277047 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0409. Min Act: -0.0000

Data Index: 140518 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1332415 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9898. Min Act: -0.0000

Data Index: 935706 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9508. Min Act: -0.0000

Data Index: 155661 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9652. Min Act: -0.0000

Data Index: 144148 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.8180. Min Act: -0.0000

Data Index: 788385 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9527. Min Act: -0.0000

Data Index: 920713 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9884. Min Act: -0.0000

Data Index: 18879 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9301. Min Act: -0.0000

Data Index: 90044 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9220. Min Act: -0.0000

Data Index: 898020 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9693. Min Act: -0.0000

Data Index: 346455 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9021. Min Act: -0.0000

Data Index: 106759 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9319. Min Act: -0.0000

Data Index: 575846 (C4 (Web Text))

Max Activating Token Index: 399