Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 299 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0450. Min Act: -0.0002

Data Index: 857313 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0001

Data Index: 528048 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1500216 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0408. Min Act: -0.0001

Data Index: 335771 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0407. Min Act: -0.0002

Data Index: 362521 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0416. Min Act: -0.0002

Data Index: 713119 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0409. Min Act: -0.0002

Data Index: 934674 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1022183 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0399. Min Act: -0.0002

Data Index: 992726 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0398. Min Act: -0.0002

Data Index: 760606 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0388. Min Act: -0.0002

Data Index: 447324 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0367. Min Act: -0.0002

Data Index: 340748 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0382. Min Act: -0.0001

Data Index: 90456 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1532852 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0371. Min Act: -0.0002

Data Index: 458799 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0373. Min Act: -0.0002

Data Index: 756150 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1150541 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0379. Min Act: -0.0002

Data Index: 370510 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0376. Min Act: -0.0002

Data Index: 977799 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0353. Min Act: -0.0001

Data Index: 369885 (C4 (Web Text))

Max Activating Token Index: 234