Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0974. Min Act: -0.0000

Data Index: 985779 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1108638 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0633. Min Act: -0.0000

Data Index: 929333 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9923. Min Act: -0.0000

Data Index: 310658 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0044. Min Act: -0.0000

Data Index: 936738 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.1223. Min Act: -0.0000

Data Index: 263002 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0114. Min Act: -0.0000

Data Index: 460664 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 1.1223. Min Range: -1.1223

Max Act: 1.0060. Min Act: -0.0000

Data Index: 174405 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9664. Min Act: -0.0000

Data Index: 809497 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1517847 (Python Code)

Max Activating Token Index: 560

Text #10

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9129. Min Act: -0.0000

Data Index: 808551 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1335007 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1306882 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9049. Min Act: -0.0000

Data Index: 582563 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1149473 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.8820. Min Act: -0.0000

Data Index: 799715 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.7312. Min Act: -0.0000

Data Index: 671323 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.8456. Min Act: -0.0000

Data Index: 972343 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.7429. Min Act: -0.0000

Data Index: 541701 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.8204. Min Act: -0.0000

Data Index: 862049 (C4 (Web Text))

Max Activating Token Index: 958