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

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

Neuron 2451 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: 3.2404. Min Range: -3.2404

Max Act: 3.2404. Min Act: -0.0000

Data Index: 789483 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.7182. Min Act: -0.0000

Data Index: 262730 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.6311. Min Act: -0.0000

Data Index: 188012 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.4801. Min Act: -0.0000

Data Index: 305642 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.4592. Min Act: -0.0000

Data Index: 764118 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.4262. Min Act: -0.0000

Data Index: 1043493 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.6722. Min Act: -0.0000

Data Index: 964970 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.3770. Min Act: -0.0000

Data Index: 1089214 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.4337. Min Act: -0.0000

Data Index: 739522 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.4889. Min Act: -0.0000

Data Index: 749186 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.0927. Min Act: -0.0000

Data Index: 899537 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.0674. Min Act: -0.0000

Data Index: 1100288 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.0444. Min Act: -0.0000

Data Index: 423615 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 3.2404. Min Range: -3.2404

Max Act: 1.9571. Min Act: -0.0000

Data Index: 1566457 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 3.2404. Min Range: -3.2404

Max Act: 1.9675. Min Act: -0.0000

Data Index: 32063 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 3.2404. Min Range: -3.2404

Max Act: 1.8224. Min Act: -0.0000

Data Index: 493831 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.0175. Min Act: -0.0000

Data Index: 826360 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 3.2404. Min Range: -3.2404

Max Act: 2.0163. Min Act: -0.0000

Data Index: 827782 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 3.2404. Min Range: -3.2404

Max Act: 1.8847. Min Act: -0.0000

Data Index: 772485 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 3.2404. Min Range: -3.2404

Max Act: 1.9698. Min Act: -0.0000

Data Index: 1330812 (C4 (Web Text))

Max Activating Token Index: 21