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

Dataset: The Pile

Neuron 236 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7280. Min Act: -0.0000

Data Index: 109616 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7677. Min Act: -0.0000

Data Index: 504065 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7617. Min Act: -0.0000

Data Index: 165799 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7255. Min Act: -0.0000

Data Index: 57949 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6508. Min Act: -0.0000

Data Index: 708094 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1303611 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6251. Min Act: -0.0000

Data Index: 527835 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6326. Min Act: -0.0000

Data Index: 433423 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1729431 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5703. Min Act: -0.0000

Data Index: 270619 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1973308 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6082. Min Act: -0.0000

Data Index: 794165 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1457582 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1352227 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5299. Min Act: -0.0000

Data Index: 275892 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5578. Min Act: -0.0000

Data Index: 692010 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5456. Min Act: -0.0000

Data Index: 280981 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1635254 (The Pile)

Max Activating Token Index: 509

Text #18

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6014. Min Act: -0.0000

Data Index: 119564 (The Pile)

Max Activating Token Index: 602

Text #19

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1548336 (The Pile)

Max Activating Token Index: 243