Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 519 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1122429 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1075240 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1193806 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1307465 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0401. Min Act: -0.0002

Data Index: 792984 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0426. Min Act: -0.0002

Data Index: 617886 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1013290 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0388. Min Act: -0.0002

Data Index: 957492 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0392. Min Act: -0.0002

Data Index: 869175 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0386. Min Act: -0.0002

Data Index: 149518 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1151785 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1073599 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0356. Min Act: -0.0002

Data Index: 108169 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1037072 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1358712 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0338. Min Act: -0.0002

Data Index: 903027 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0333. Min Act: -0.0002

Data Index: 51307 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0320. Min Act: -0.0002

Data Index: 678132 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0314. Min Act: -0.0002

Data Index: 647374 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0308. Min Act: -0.0002

Data Index: 230448 (C4 (Web Text))

Max Activating Token Index: 299