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

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

Neuron 4245 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1637792 (Python Code)

Max Activating Token Index: 682

Text #1

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0440. Min Act: -0.0001

Data Index: 761569 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0484. Min Act: -0.0001

Data Index: 835092 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0435. Min Act: -0.0001

Data Index: 436531 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0477. Min Act: -0.0001

Data Index: 182755 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1050181 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0426. Min Act: -0.0001

Data Index: 75111 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0424. Min Act: -0.0001

Data Index: 509991 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0436. Min Act: -0.0001

Data Index: 295698 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1211549 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1110656 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0399. Min Act: -0.0001

Data Index: 590768 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0427. Min Act: -0.0001

Data Index: 851530 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1065967 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0401. Min Act: -0.0001

Data Index: 988533 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0373. Min Act: -0.0001

Data Index: 154846 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0401. Min Act: -0.0001

Data Index: 251755 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0382. Min Act: -0.0001

Data Index: 985728 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0412. Min Act: -0.0001

Data Index: 412597 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0354. Min Act: -0.0001

Data Index: 414259 (C4 (Web Text))

Max Activating Token Index: 360