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

Dataset: The Pile

Neuron 2102 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1374625 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.5149. Min Act: -0.0000

Data Index: 663217 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1311540 (The Pile)

Max Activating Token Index: 207

Text #3

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3602. Min Act: -0.0000

Data Index: 447820 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3503. Min Act: -0.0000

Data Index: 133540 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3502. Min Act: -0.0000

Data Index: 28454 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3340. Min Act: -0.0000

Data Index: 249528 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1819652 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3810. Min Act: -0.0000

Data Index: 446920 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3184. Min Act: -0.0000

Data Index: 547011 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3225. Min Act: -0.0000

Data Index: 723780 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1660636 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1224149 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1397040 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1480980 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.2828. Min Act: -0.0000

Data Index: 277364 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1514610 (The Pile)

Max Activating Token Index: 188

Text #17

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1858020 (The Pile)

Max Activating Token Index: 850

Text #18

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1149469 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.2961. Min Act: -0.0000

Data Index: 58532 (The Pile)

Max Activating Token Index: 652