Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1819 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0883. Min Act: -0.0005

Data Index: 89049 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0809. Min Act: -0.0005

Data Index: 1261830 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0752. Min Act: -0.0005

Data Index: 724326 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0688. Min Act: -0.0005

Data Index: 786586 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0684. Min Act: -0.0005

Data Index: 123386 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0660. Min Act: -0.0005

Data Index: 309388 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0669. Min Act: -0.0005

Data Index: 1179 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0654. Min Act: -0.0005

Data Index: 1269760 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0661. Min Act: -0.0005

Data Index: 314756 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0638. Min Act: -0.0005

Data Index: 986421 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0628. Min Act: -0.0005

Data Index: 885063 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0601. Min Act: -0.0005

Data Index: 393649 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0633. Min Act: -0.0005

Data Index: 1299852 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0632. Min Act: -0.0005

Data Index: 63335 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0629. Min Act: -0.0005

Data Index: 572801 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0621. Min Act: -0.0005

Data Index: 105910 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0598. Min Act: -0.0005

Data Index: 1046292 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0627. Min Act: -0.0005

Data Index: 1273320 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0609. Min Act: -0.0005

Data Index: 231616 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0610. Min Act: -0.0005

Data Index: 20459 (C4 (Web Text))

Max Activating Token Index: 783