Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 394 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.9216. Min Act: 0.0001

Data Index: 1475143 (Python Code)

Max Activating Token Index: 982

Text #1

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.9087. Min Act: 0.0001

Data Index: 1449238 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.6850. Min Act: 0.0001

Data Index: 1646410 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.1883. Min Act: 0.0001

Data Index: 1539549 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.1760. Min Act: 0.0001

Data Index: 1585363 (Python Code)

Max Activating Token Index: 450

Text #5

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.1468. Min Act: -0.0000

Data Index: 49761 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.1270. Min Act: 0.0001

Data Index: 1534294 (Python Code)

Max Activating Token Index: 424

Text #7

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.0617. Min Act: 0.0001

Data Index: 1459996 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.0645. Min Act: 0.0001

Data Index: 1526843 (Python Code)

Max Activating Token Index: 495

Text #9

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.0349. Min Act: 0.0000

Data Index: 1101789 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1467835 (Python Code)

Max Activating Token Index: 977

Text #11

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.0163. Min Act: 0.0001

Data Index: 1628906 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 1.9216. Min Range: -1.9216

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1159227 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 1.9216. Min Range: -1.9216

Max Act: 0.9335. Min Act: 0.0001

Data Index: 1642423 (Python Code)

Max Activating Token Index: 916

Text #14

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.0248. Min Act: -0.0000

Data Index: 529354 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 1.9216. Min Range: -1.9216

Max Act: 0.8958. Min Act: -0.0000

Data Index: 440384 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.9216. Min Range: -1.9216

Max Act: 0.9999. Min Act: 0.0001

Data Index: 1577572 (Python Code)

Max Activating Token Index: 730

Text #17

Max Range: 1.9216. Min Range: -1.9216

Max Act: 0.8935. Min Act: 0.0001

Data Index: 1431439 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 1.9216. Min Range: -1.9216

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1337704 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 1.9216. Min Range: -1.9216

Max Act: 0.9235. Min Act: 0.0001

Data Index: 1442189 (Python Code)

Max Activating Token Index: 992