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

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

Neuron 4967 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1598659 (Python Code)

Max Activating Token Index: 648

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0470. Min Act: -0.0001

Data Index: 425171 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1618012 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1595512 (Python Code)

Max Activating Token Index: 782

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0421. Min Act: -0.0001

Data Index: 784777 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1299663 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0449. Min Act: -0.0001

Data Index: 145603 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1236140 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0407. Min Act: -0.0001

Data Index: 46462 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1529026 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1448291 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1049964 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0390. Min Act: -0.0001

Data Index: 187864 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0410. Min Act: -0.0001

Data Index: 680101 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1485035 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0363. Min Act: -0.0001

Data Index: 878638 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1611814 (Python Code)

Max Activating Token Index: 73

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1623874 (Python Code)

Max Activating Token Index: 127

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1362241 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0373. Min Act: -0.0001

Data Index: 724727 (C4 (Web Text))

Max Activating Token Index: 103