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

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

Neuron 399 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: 0.0596. Min Range: -0.0596

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1439452 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0546. Min Act: -0.0003

Data Index: 436835 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1364400 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0532. Min Act: -0.0003

Data Index: 758577 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0520. Min Act: -0.0004

Data Index: 1514317 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1510149 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1476987 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1283753 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1600626 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0474. Min Act: -0.0002

Data Index: 629989 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1307066 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0471. Min Act: -0.0003

Data Index: 691393 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1640398 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1523454 (Python Code)

Max Activating Token Index: 546

Text #14

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0478. Min Act: -0.0003

Data Index: 23910 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1487670 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0472. Min Act: -0.0003

Data Index: 452692 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1076344 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1483203 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1369614 (Python Code)

Max Activating Token Index: 679