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

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

Neuron 268 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0006

Data Index: 1062109 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0418. Min Act: -0.0006

Data Index: 28184 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0445. Min Act: -0.0006

Data Index: 23615 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0451. Min Act: -0.0006

Data Index: 1075684 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0422. Min Act: -0.0006

Data Index: 1088519 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0426. Min Act: -0.0006

Data Index: 733546 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0417. Min Act: -0.0006

Data Index: 1358477 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0426. Min Act: -0.0006

Data Index: 373028 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1341832 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0422. Min Act: -0.0006

Data Index: 617001 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0386. Min Act: -0.0006

Data Index: 678732 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0391. Min Act: -0.0006

Data Index: 151228 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0370. Min Act: -0.0006

Data Index: 713880 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1259663 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0389. Min Act: -0.0006

Data Index: 467199 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0386. Min Act: -0.0006

Data Index: 789084 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0390. Min Act: -0.0006

Data Index: 887393 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0347. Min Act: -0.0006

Data Index: 1127661 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0437. Min Act: -0.0006

Data Index: 608434 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0389. Min Act: -0.0006

Data Index: 418382 (C4 (Web Text))

Max Activating Token Index: 479