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

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

Neuron 3506 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: 2.6279. Min Range: -2.6279

Max Act: 2.6279. Min Act: -0.0000

Data Index: 1446430 (Python Code)

Max Activating Token Index: 573

Text #1

Max Range: 2.6279. Min Range: -2.6279

Max Act: 2.5699. Min Act: -0.0000

Data Index: 1536321 (Python Code)

Max Activating Token Index: 837

Text #2

Max Range: 2.6279. Min Range: -2.6279

Max Act: 2.4817. Min Act: -0.0000

Data Index: 1476007 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 2.6279. Min Range: -2.6279

Max Act: 2.2163. Min Act: -0.0000

Data Index: 1423031 (Python Code)

Max Activating Token Index: 822

Text #4

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.9453. Min Act: -0.0000

Data Index: 1400851 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1530026 (Python Code)

Max Activating Token Index: 365

Text #6

Max Range: 2.6279. Min Range: -2.6279

Max Act: 2.0218. Min Act: -0.0001

Data Index: 1468820 (Python Code)

Max Activating Token Index: 445

Text #7

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.9703. Min Act: -0.0000

Data Index: 1383878 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1370577 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 2.6279. Min Range: -2.6279

Max Act: 2.0384. Min Act: -0.0001

Data Index: 1490387 (Python Code)

Max Activating Token Index: 325

Text #10

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.8155. Min Act: -0.0000

Data Index: 1527750 (Python Code)

Max Activating Token Index: 464

Text #11

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.9142. Min Act: -0.0001

Data Index: 1602751 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.9857. Min Act: -0.0001

Data Index: 1441028 (Python Code)

Max Activating Token Index: 971

Text #13

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.7758. Min Act: -0.0001

Data Index: 1384775 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.7431. Min Act: -0.0000

Data Index: 1372694 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.9387. Min Act: -0.0000

Data Index: 1401808 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.9234. Min Act: -0.0000

Data Index: 1577695 (Python Code)

Max Activating Token Index: 794

Text #17

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.7970. Min Act: -0.0000

Data Index: 1552898 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.8874. Min Act: -0.0000

Data Index: 1440769 (Python Code)

Max Activating Token Index: 694

Text #19

Max Range: 2.6279. Min Range: -2.6279

Max Act: 1.6748. Min Act: -0.0000

Data Index: 1471989 (Python Code)

Max Activating Token Index: 890