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

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

Neuron 227 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1641768 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1494624 (Python Code)

Max Activating Token Index: 840

Text #2

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1516714 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1380865 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1636764 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1591096 (Python Code)

Max Activating Token Index: 330

Text #6

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1417699 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1618344 (Python Code)

Max Activating Token Index: 540

Text #8

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1385105 (Python Code)

Max Activating Token Index: 392

Text #9

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1480770 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1498658 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1654471 (Python Code)

Max Activating Token Index: 696

Text #12

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1596775 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1488796 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1478842 (Python Code)

Max Activating Token Index: 495

Text #15

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1593106 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1385296 (Python Code)

Max Activating Token Index: 707

Text #17

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1647367 (Python Code)

Max Activating Token Index: 392

Text #18

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1561143 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1404513 (Python Code)

Max Activating Token Index: 537