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

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

Neuron 5513 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6399. Min Range: -6.6399

Max Act: 6.6399. Min Act: -0.0000

Data Index: 966668 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 6.6399. Min Range: -6.6399

Max Act: 5.7457. Min Act: -0.0000

Data Index: 664425 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 6.6399. Min Range: -6.6399

Max Act: 5.5008. Min Act: -0.0000

Data Index: 799575 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 6.6399. Min Range: -6.6399

Max Act: 5.1105. Min Act: -0.0000

Data Index: 1275245 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 6.6399. Min Range: -6.6399

Max Act: 5.0416. Min Act: -0.0000

Data Index: 1033947 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.6615. Min Act: -0.0000

Data Index: 812304 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.7888. Min Act: -0.0000

Data Index: 1071535 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.5074. Min Act: -0.0000

Data Index: 891480 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.5211. Min Act: -0.0000

Data Index: 175604 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.5647. Min Act: -0.0000

Data Index: 95817 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 6.6399. Min Range: -6.6399

Max Act: 3.8169. Min Act: -0.0000

Data Index: 532061 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.0933. Min Act: -0.0000

Data Index: 691689 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.2782. Min Act: -0.0000

Data Index: 217661 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.0824. Min Act: -0.0000

Data Index: 1271439 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.3185. Min Act: -0.0000

Data Index: 1106004 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 6.6399. Min Range: -6.6399

Max Act: 3.8845. Min Act: -0.0000

Data Index: 681439 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.2934. Min Act: -0.0000

Data Index: 24148 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.0691. Min Act: -0.0000

Data Index: 1094903 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.2167. Min Act: -0.0000

Data Index: 1074199 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 6.6399. Min Range: -6.6399

Max Act: 4.1606. Min Act: -0.0000

Data Index: 455672 (C4 (Web Text))

Max Activating Token Index: 502