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

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

Neuron 1971 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: 0.0482. Min Range: -0.0482

Max Act: 0.0482. Min Act: -0.0003

Data Index: 902520 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0434. Min Act: -0.0003

Data Index: 768912 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0422. Min Act: -0.0003

Data Index: 688583 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0422. Min Act: -0.0003

Data Index: 453921 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0420. Min Act: -0.0003

Data Index: 986080 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0396. Min Act: -0.0003

Data Index: 969679 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0397. Min Act: -0.0003

Data Index: 505229 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0390. Min Act: -0.0003

Data Index: 600660 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1296239 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0399. Min Act: -0.0003

Data Index: 881887 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1050808 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0381. Min Act: -0.0003

Data Index: 406318 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1154999 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1260344 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1128013 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0376. Min Act: -0.0003

Data Index: 282603 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0375. Min Act: -0.0003

Data Index: 710100 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0365. Min Act: -0.0003

Data Index: 520041 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0374. Min Act: -0.0003

Data Index: 613083 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0366. Min Act: -0.0003

Data Index: 792554 (C4 (Web Text))

Max Activating Token Index: 555