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

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

Neuron 2695 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1469930 (Python Code)

Max Activating Token Index: 789

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1516383 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1317011 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0365. Min Act: -0.0000

Data Index: 213900 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1426282 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1562007 (Python Code)

Max Activating Token Index: 625

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1570809 (Python Code)

Max Activating Token Index: 823

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1374820 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0344. Min Act: -0.0000

Data Index: 61017 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1433050 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1579543 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1401855 (Python Code)

Max Activating Token Index: 613

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1484159 (Python Code)

Max Activating Token Index: 298

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0311. Min Act: -0.0000

Data Index: 1372159 (Python Code)

Max Activating Token Index: 301

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1635548 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1355655 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1557930 (Python Code)

Max Activating Token Index: 701

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1536735 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1408250 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1272267 (C4 (Web Text))

Max Activating Token Index: 736