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

Dataset: The Pile

Neuron 847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1704087 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1729942 (The Pile)

Max Activating Token Index: 803

Text #2

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1611. Min Act: -0.0000

Data Index: 377695 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.9425. Min Act: -0.0000

Data Index: 998274 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1930351 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.9983. Min Act: -0.0000

Data Index: 528412 (The Pile)

Max Activating Token Index: 149

Text #6

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.9232. Min Act: -0.0000

Data Index: 232105 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1641074 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.9813. Min Act: -0.0000

Data Index: 427611 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.9105. Min Act: -0.0000

Data Index: 355175 (The Pile)

Max Activating Token Index: 563

Text #10

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.8685. Min Act: -0.0000

Data Index: 570829 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1489613 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.9478. Min Act: -0.0000

Data Index: 330660 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.8807. Min Act: -0.0000

Data Index: 139941 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1705592 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1942967 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.9278. Min Act: -0.0000

Data Index: 459855 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1649895 (The Pile)

Max Activating Token Index: 844

Text #18

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1245545 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 1.3352. Min Range: -1.3352

Max Act: 0.7794. Min Act: -0.0000

Data Index: 27975 (The Pile)

Max Activating Token Index: 317