Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 344 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.3213. Min Act: -0.0003

Data Index: 818969 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2663. Min Act: -0.0003

Data Index: 863354 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2750. Min Act: -0.0003

Data Index: 1314027 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2692. Min Act: -0.0003

Data Index: 443738 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2580. Min Act: -0.0003

Data Index: 1037792 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2683. Min Act: -0.0003

Data Index: 540436 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2515. Min Act: -0.0003

Data Index: 1289684 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2558. Min Act: -0.0003

Data Index: 309998 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2634. Min Act: -0.0003

Data Index: 313747 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2510. Min Act: -0.0003

Data Index: 677555 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2511. Min Act: -0.0003

Data Index: 78760 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2445. Min Act: -0.0003

Data Index: 126147 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2437. Min Act: -0.0003

Data Index: 1214556 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2338. Min Act: -0.0003

Data Index: 1304603 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2417. Min Act: -0.0003

Data Index: 224023 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2325. Min Act: -0.0003

Data Index: 386817 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2393. Min Act: -0.0003

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2389. Min Act: -0.0003

Data Index: 815984 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2313. Min Act: -0.0003

Data Index: 1057202 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2386. Min Act: -0.0003

Data Index: 1351493 (C4 (Web Text))

Max Activating Token Index: 64