Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3217 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0444. Min Act: -0.0002

Data Index: 738714 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0429. Min Act: -0.0002

Data Index: 961732 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0394. Min Act: -0.0002

Data Index: 353287 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1490270 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0410. Min Act: -0.0002

Data Index: 214608 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1015503 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0402. Min Act: -0.0002

Data Index: 669576 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0398. Min Act: -0.0002

Data Index: 725751 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0395. Min Act: -0.0002

Data Index: 449195 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0338. Min Act: -0.0002

Data Index: 227996 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1615670 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1437944 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0342. Min Act: -0.0002

Data Index: 759918 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0336. Min Act: -0.0002

Data Index: 504372 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0341. Min Act: -0.0002

Data Index: 112987 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1417056 (Python Code)

Max Activating Token Index: 424

Text #16

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0336. Min Act: -0.0002

Data Index: 898854 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0368. Min Act: -0.0002

Data Index: 327876 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0349. Min Act: -0.0002

Data Index: 211048 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0349. Min Act: -0.0002

Data Index: 680716 (C4 (Web Text))

Max Activating Token Index: 881