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

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

Neuron 3868 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.5546. Min Act: -0.0000

Data Index: 1034454 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.5380. Min Act: -0.0000

Data Index: 961318 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.3656. Min Act: -0.0000

Data Index: 329032 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.3439. Min Act: -0.0000

Data Index: 1142815 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.2989. Min Act: -0.0000

Data Index: 161539 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.1592. Min Act: -0.0000

Data Index: 879369 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.3540. Min Act: -0.0000

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.1180. Min Act: -0.0000

Data Index: 382666 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.2241. Min Act: -0.0000

Data Index: 775480 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.0712. Min Act: -0.0000

Data Index: 548134 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.0803. Min Act: -0.0000

Data Index: 309069 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.1643. Min Act: -0.0000

Data Index: 133450 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.2531. Min Act: -0.0000

Data Index: 734941 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 2.5546. Min Range: -2.5546

Max Act: 1.9655. Min Act: -0.0000

Data Index: 1223894 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.1270. Min Act: -0.0000

Data Index: 659158 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.1089. Min Act: -0.0000

Data Index: 52064 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.1035. Min Act: -0.0000

Data Index: 1034951 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 2.5546. Min Range: -2.5546

Max Act: 1.8543. Min Act: -0.0000

Data Index: 512995 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 2.5546. Min Range: -2.5546

Max Act: 2.0535. Min Act: -0.0000

Data Index: 902076 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 2.5546. Min Range: -2.5546

Max Act: 1.8100. Min Act: -0.0000

Data Index: 732140 (C4 (Web Text))

Max Activating Token Index: 840