Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 432 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0003

Data Index: 346810 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0612. Min Act: -0.0003

Data Index: 601822 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0548. Min Act: -0.0003

Data Index: 600711 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1059062 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0472. Min Act: -0.0003

Data Index: 96838 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0463. Min Act: -0.0003

Data Index: 879338 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0454. Min Act: -0.0003

Data Index: 805828 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1099087 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0444. Min Act: -0.0003

Data Index: 55007 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1332120 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0440. Min Act: -0.0003

Data Index: 9921 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0426. Min Act: -0.0002

Data Index: 503710 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0441. Min Act: -0.0002

Data Index: 990407 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1145892 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0438. Min Act: -0.0002

Data Index: 800410 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0438. Min Act: -0.0003

Data Index: 714886 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1133396 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1058235 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0419. Min Act: -0.0003

Data Index: 896223 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0417. Min Act: -0.0003

Data Index: 297982 (C4 (Web Text))

Max Activating Token Index: 570