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

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

Neuron 3372 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4278. Min Act: -0.0002

Data Index: 894211 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5714. Min Act: -0.0002

Data Index: 557312 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.3601. Min Act: -0.0002

Data Index: 1267796 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.3332. Min Act: -0.0002

Data Index: 1315854 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1427. Min Act: -0.0002

Data Index: 1088162 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1044. Min Act: -0.0002

Data Index: 824812 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1464. Min Act: -0.0002

Data Index: 53766 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0870. Min Act: -0.0002

Data Index: 1214866 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0637. Min Act: -0.0002

Data Index: 283027 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0718. Min Act: -0.0002

Data Index: 385214 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0319. Min Act: -0.0002

Data Index: 549194 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9779. Min Act: -0.0002

Data Index: 805068 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9774. Min Act: -0.0002

Data Index: 1264561 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0626. Min Act: -0.0002

Data Index: 1126864 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9970. Min Act: -0.0002

Data Index: 930959 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9591. Min Act: -0.0002

Data Index: 502808 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9715. Min Act: -0.0002

Data Index: 528568 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9577. Min Act: -0.0002

Data Index: 672127 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9644. Min Act: -0.0002

Data Index: 957213 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0049. Min Act: -0.0002

Data Index: 582547 (C4 (Web Text))

Max Activating Token Index: 697