Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 825 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1475843 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0408. Min Act: -0.0003

Data Index: 177678 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1180678 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1382683 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1561118 (Python Code)

Max Activating Token Index: 630

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0352. Min Act: -0.0002

Data Index: 595267 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1380658 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1644186 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0352. Min Act: -0.0003

Data Index: 249516 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1618811 (Python Code)

Max Activating Token Index: 350

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1607854 (Python Code)

Max Activating Token Index: 75

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1510770 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1345007 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1608295 (Python Code)

Max Activating Token Index: 424

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1591081 (Python Code)

Max Activating Token Index: 884

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1609888 (Python Code)

Max Activating Token Index: 961

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0351. Min Act: -0.0002

Data Index: 453626 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0343. Min Act: -0.0003

Data Index: 462 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1249154 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0340. Min Act: -0.0003

Data Index: 127091 (C4 (Web Text))

Max Activating Token Index: 214