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

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

Neuron 2535 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.2138. Min Act: -0.0001

Data Index: 704555 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1555. Min Act: -0.0001

Data Index: 424161 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1579. Min Act: -0.0001

Data Index: 547872 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1522714 (Python Code)

Max Activating Token Index: 916

Text #4

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1414. Min Act: -0.0001

Data Index: 587217 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1523. Min Act: -0.0001

Data Index: 803145 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1508. Min Act: -0.0001

Data Index: 28269 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1486. Min Act: -0.0001

Data Index: 460297 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1449. Min Act: -0.0001

Data Index: 539720 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1481. Min Act: -0.0001

Data Index: 32425 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1198988 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1402. Min Act: -0.0001

Data Index: 354329 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1442709 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1349. Min Act: -0.0001

Data Index: 674417 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1255105 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1347. Min Act: -0.0001

Data Index: 2849 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1044672 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1303. Min Act: -0.0001

Data Index: 854480 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1397. Min Act: -0.0001

Data Index: 722316 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1473881 (Python Code)

Max Activating Token Index: 775