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

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

Neuron 2576 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: 4.5945. Min Range: -4.5945

Max Act: 4.5945. Min Act: -0.0001

Data Index: 718736 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 4.5945. Min Range: -4.5945

Max Act: 4.3181. Min Act: -0.0000

Data Index: 540571 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 4.5945. Min Range: -4.5945

Max Act: 4.0169. Min Act: -0.0000

Data Index: 620689 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 4.5945. Min Range: -4.5945

Max Act: 4.1406. Min Act: -0.0000

Data Index: 1148146 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.9604. Min Act: -0.0000

Data Index: 166913 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.5520. Min Act: -0.0000

Data Index: 1143853 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.4831. Min Act: -0.0000

Data Index: 420002 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.5469. Min Act: -0.0000

Data Index: 462692 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.2740. Min Act: -0.0000

Data Index: 131614 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.5677. Min Act: -0.0000

Data Index: 117393 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.5775. Min Act: -0.0000

Data Index: 1330903 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.3513. Min Act: -0.0000

Data Index: 571380 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.3651. Min Act: -0.0000

Data Index: 1229197 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.4199. Min Act: -0.0000

Data Index: 653750 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.3939. Min Act: -0.0000

Data Index: 751115 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.0550. Min Act: -0.0000

Data Index: 1284412 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.3445. Min Act: -0.0000

Data Index: 684782 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.1728. Min Act: -0.0000

Data Index: 1045975 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 4.5945. Min Range: -4.5945

Max Act: 3.2934. Min Act: -0.0000

Data Index: 260569 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 4.5945. Min Range: -4.5945

Max Act: 2.8657. Min Act: -0.0000

Data Index: 632807 (C4 (Web Text))

Max Activating Token Index: 976