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

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

Neuron 21 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: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0005

Data Index: 528791 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0005

Data Index: 642559 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0564. Min Act: -0.0005

Data Index: 1025463 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0533. Min Act: -0.0005

Data Index: 1306004 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0549. Min Act: -0.0005

Data Index: 539762 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0550. Min Act: -0.0005

Data Index: 880012 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0511. Min Act: -0.0005

Data Index: 726086 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0482. Min Act: -0.0005

Data Index: 583437 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0510. Min Act: -0.0005

Data Index: 1167975 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0493. Min Act: -0.0005

Data Index: 209534 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0484. Min Act: -0.0005

Data Index: 714405 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0502. Min Act: -0.0005

Data Index: 547809 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0483. Min Act: -0.0005

Data Index: 344619 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0500. Min Act: -0.0005

Data Index: 317528 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0503. Min Act: -0.0005

Data Index: 817316 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0467. Min Act: -0.0005

Data Index: 462176 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0442. Min Act: -0.0005

Data Index: 133141 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0487. Min Act: -0.0005

Data Index: 15960 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0487. Min Act: -0.0005

Data Index: 154156 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0494. Min Act: -0.0005

Data Index: 1196405 (C4 (Web Text))

Max Activating Token Index: 901