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

Dataset: The Pile

Neuron 1252 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1479229 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.2288. Min Act: -0.0000

Data Index: 285955 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1612664 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.0282. Min Act: -0.0000

Data Index: 1166421 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.0423. Min Act: -0.0000

Data Index: 890863 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.0487. Min Act: -0.0000

Data Index: 1188980 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1540837 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1571226 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1273374 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9298. Min Act: -0.0000

Data Index: 529766 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9435. Min Act: -0.0000

Data Index: 523437 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1919577 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 1.3407. Min Range: -1.3407

Max Act: 1.0148. Min Act: -0.0000

Data Index: 209437 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1435442 (The Pile)

Max Activating Token Index: 309

Text #14

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1346845 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1918069 (The Pile)

Max Activating Token Index: 992

Text #16

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9606. Min Act: -0.0000

Data Index: 241091 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1972584 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.8798. Min Act: -0.0000

Data Index: 91398 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.3407. Min Range: -1.3407

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1274355 (The Pile)

Max Activating Token Index: 761