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

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

Neuron 5483 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: 3.7244. Min Range: -3.7244

Max Act: 3.6990. Min Act: -0.0000

Data Index: 1521127 (Python Code)

Max Activating Token Index: 637

Text #1

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.5907. Min Act: 0.0000

Data Index: 1448150 (Python Code)

Max Activating Token Index: 401

Text #2

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.7244. Min Act: 0.0001

Data Index: 1393558 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.3931. Min Act: 0.0000

Data Index: 1569668 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.5143. Min Act: 0.0000

Data Index: 1643345 (Python Code)

Max Activating Token Index: 685

Text #5

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.4990. Min Act: -0.0000

Data Index: 1641267 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.4778. Min Act: -0.0000

Data Index: 1363661 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1167. Min Act: -0.0000

Data Index: 1403824 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.3921. Min Act: -0.0000

Data Index: 1379728 (Python Code)

Max Activating Token Index: 696

Text #9

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.4622. Min Act: 0.0000

Data Index: 1566831 (Python Code)

Max Activating Token Index: 397

Text #10

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.4505. Min Act: 0.0000

Data Index: 1393947 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1427. Min Act: -0.0000

Data Index: 1364432 (Python Code)

Max Activating Token Index: 914

Text #12

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.0828. Min Act: 0.0000

Data Index: 1502204 (Python Code)

Max Activating Token Index: 681

Text #13

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1756. Min Act: -0.0000

Data Index: 1407021 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 3.7244. Min Range: -3.7244

Max Act: 2.9613. Min Act: 0.0001

Data Index: 1594211 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.0918. Min Act: -0.0000

Data Index: 1588217 (Python Code)

Max Activating Token Index: 1004

Text #16

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.0871. Min Act: -0.0000

Data Index: 1618577 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1930. Min Act: -0.0000

Data Index: 1384394 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1510. Min Act: -0.0000

Data Index: 1486810 (Python Code)

Max Activating Token Index: 683

Text #19

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.0026. Min Act: -0.0000

Data Index: 1399451 (Python Code)

Max Activating Token Index: 415