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

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

Neuron 2991 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: 0.0443. Min Range: -0.0443

Max Act: 0.0443. Min Act: -0.0002

Data Index: 733015 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0437. Min Act: -0.0002

Data Index: 93144 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0437. Min Act: -0.0002

Data Index: 542492 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0427. Min Act: -0.0002

Data Index: 129592 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0424. Min Act: -0.0002

Data Index: 839468 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1061482 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0395. Min Act: -0.0002

Data Index: 327971 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1009158 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1258569 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0376. Min Act: -0.0002

Data Index: 926341 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0384. Min Act: -0.0002

Data Index: 199998 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0379. Min Act: -0.0002

Data Index: 820263 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0377. Min Act: -0.0002

Data Index: 568904 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0376. Min Act: -0.0002

Data Index: 980214 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1246854 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0376. Min Act: -0.0002

Data Index: 246741 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0371. Min Act: -0.0002

Data Index: 987277 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1141025 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0374. Min Act: -0.0002

Data Index: 76609 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0365. Min Act: -0.0002

Data Index: 480318 (C4 (Web Text))

Max Activating Token Index: 116