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

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

Neuron 1845 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: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0001

Data Index: 102042 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0411. Min Act: -0.0002

Data Index: 749241 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1585335 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0002

Data Index: 780914 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0425. Min Act: -0.0002

Data Index: 225943 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1125712 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1030458 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0419. Min Act: -0.0002

Data Index: 706429 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0417. Min Act: -0.0002

Data Index: 798438 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0410. Min Act: -0.0002

Data Index: 887307 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0405. Min Act: -0.0002

Data Index: 708776 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1162941 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0415. Min Act: -0.0002

Data Index: 665535 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1069641 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0403. Min Act: -0.0002

Data Index: 877603 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0388. Min Act: -0.0002

Data Index: 590056 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1021749 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0405. Min Act: -0.0002

Data Index: 325042 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0391. Min Act: -0.0002

Data Index: 85810 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1321730 (C4 (Web Text))

Max Activating Token Index: 253