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

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

Neuron 1600 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: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0002

Data Index: 523894 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1143126 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1262360 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0425. Min Act: -0.0002

Data Index: 163292 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0420. Min Act: -0.0002

Data Index: 822925 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0427. Min Act: -0.0002

Data Index: 839489 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0418. Min Act: -0.0002

Data Index: 50044 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0412. Min Act: -0.0002

Data Index: 413939 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0414. Min Act: -0.0002

Data Index: 302543 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0414. Min Act: -0.0002

Data Index: 402290 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0398. Min Act: -0.0002

Data Index: 486515 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0396. Min Act: -0.0002

Data Index: 21719 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0393. Min Act: -0.0002

Data Index: 113389 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0407. Min Act: -0.0002

Data Index: 472945 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1169030 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0394. Min Act: -0.0002

Data Index: 662037 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0377. Min Act: -0.0002

Data Index: 519621 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0385. Min Act: -0.0002

Data Index: 143560 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0371. Min Act: -0.0002

Data Index: 244236 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0376. Min Act: -0.0002

Data Index: 124586 (C4 (Web Text))

Max Activating Token Index: 262