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

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

Neuron 100 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: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0005

Data Index: 108346 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0571. Min Act: -0.0005

Data Index: 878595 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0545. Min Act: -0.0005

Data Index: 94885 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0520. Min Act: -0.0005

Data Index: 249239 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0511. Min Act: -0.0005

Data Index: 703639 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0532. Min Act: -0.0005

Data Index: 423181 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0520. Min Act: -0.0005

Data Index: 654691 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0510. Min Act: -0.0005

Data Index: 210390 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0520. Min Act: -0.0005

Data Index: 701142 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0517. Min Act: -0.0005

Data Index: 59514 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0513. Min Act: -0.0005

Data Index: 908254 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0500. Min Act: -0.0005

Data Index: 790973 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0488. Min Act: -0.0005

Data Index: 1336284 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0478. Min Act: -0.0005

Data Index: 568445 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0482. Min Act: -0.0005

Data Index: 276843 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0487. Min Act: -0.0005

Data Index: 1117050 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0479. Min Act: -0.0005

Data Index: 134939 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0480. Min Act: -0.0005

Data Index: 410211 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0488. Min Act: -0.0005

Data Index: 296998 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0484. Min Act: -0.0005

Data Index: 632707 (C4 (Web Text))

Max Activating Token Index: 553