Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2992 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.6205. Min Act: -0.0001

Data Index: 1451801 (Python Code)

Max Activating Token Index: 663

Text #1

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5635. Min Act: -0.0000

Data Index: 886468 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5763. Min Act: -0.0001

Data Index: 1456351 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5355. Min Act: -0.0001

Data Index: 1408370 (Python Code)

Max Activating Token Index: 461

Text #4

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5187. Min Act: -0.0000

Data Index: 100722 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5445. Min Act: -0.0001

Data Index: 1571571 (Python Code)

Max Activating Token Index: 461

Text #6

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5240. Min Act: -0.0001

Data Index: 1642027 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1385101 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1213489 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5032. Min Act: -0.0001

Data Index: 1446498 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1427601 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1629896 (Python Code)

Max Activating Token Index: 625

Text #12

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4754. Min Act: -0.0000

Data Index: 892826 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4901. Min Act: -0.0000

Data Index: 163175 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1631978 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4701. Min Act: -0.0001

Data Index: 1611175 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1628223 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1489833 (Python Code)

Max Activating Token Index: 544

Text #18

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1507064 (Python Code)

Max Activating Token Index: 658

Text #19

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.4770. Min Act: -0.0001

Data Index: 1627817 (Python Code)

Max Activating Token Index: 359