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

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

Neuron 1137 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: 0.4344. Min Range: -0.4344

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1378874 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1448652 (Python Code)

Max Activating Token Index: 410

Text #2

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3983. Min Act: -0.0001

Data Index: 1404537 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1531667 (Python Code)

Max Activating Token Index: 500

Text #4

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4157. Min Act: -0.0001

Data Index: 530978 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3861. Min Act: -0.0001

Data Index: 1450519 (Python Code)

Max Activating Token Index: 655

Text #6

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1621036 (Python Code)

Max Activating Token Index: 793

Text #7

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1589350 (Python Code)

Max Activating Token Index: 964

Text #8

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4052. Min Act: -0.0001

Data Index: 1549640 (Python Code)

Max Activating Token Index: 342

Text #9

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4009. Min Act: -0.0001

Data Index: 632469 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3413. Min Act: -0.0001

Data Index: 956484 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3739. Min Act: -0.0001

Data Index: 1549324 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1400112 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3618. Min Act: -0.0001

Data Index: 1417521 (Python Code)

Max Activating Token Index: 443

Text #14

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3601. Min Act: -0.0001

Data Index: 1635937 (Python Code)

Max Activating Token Index: 385

Text #15

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3536. Min Act: -0.0001

Data Index: 189792 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3400. Min Act: -0.0001

Data Index: 1251615 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3340. Min Act: -0.0001

Data Index: 824910 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3549. Min Act: -0.0001

Data Index: 1647758 (Python Code)

Max Activating Token Index: 855

Text #19

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3495. Min Act: -0.0001

Data Index: 920617 (C4 (Web Text))

Max Activating Token Index: 967