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

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

Neuron 1152 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: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1409782 (Python Code)

Max Activating Token Index: 296

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1650768 (Python Code)

Max Activating Token Index: 211

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0455. Min Act: -0.0002

Data Index: 868042 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0440. Min Act: -0.0003

Data Index: 95762 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1234499 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1294256 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0428. Min Act: -0.0003

Data Index: 148884 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1237876 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1160368 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0407. Min Act: -0.0003

Data Index: 585930 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0399. Min Act: -0.0003

Data Index: 445082 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0394. Min Act: -0.0003

Data Index: 79885 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0392. Min Act: -0.0003

Data Index: 165005 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0389. Min Act: -0.0003

Data Index: 478027 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0379. Min Act: -0.0003

Data Index: 822510 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0380. Min Act: -0.0002

Data Index: 395867 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1343558 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0375. Min Act: -0.0003

Data Index: 684698 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1456330 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0371. Min Act: -0.0003

Data Index: 799069 (C4 (Web Text))

Max Activating Token Index: 722