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

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

Neuron 1320 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: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0002

Data Index: 298496 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1468647 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1400352 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1476051 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0359. Min Act: -0.0002

Data Index: 640182 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1397264 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1626885 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1460029 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1497266 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1435084 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1459227 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1610635 (Python Code)

Max Activating Token Index: 111

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1550116 (Python Code)

Max Activating Token Index: 871

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1631884 (Python Code)

Max Activating Token Index: 1018

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1384695 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1557675 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0336. Min Act: -0.0002

Data Index: 28680 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1653987 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1589788 (Python Code)

Max Activating Token Index: 290

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1573255 (Python Code)

Max Activating Token Index: 490