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

Dataset: The Pile

Neuron 3489 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: 1.6000. Min Range: -1.6000

Max Act: 1.4008. Min Act: -0.0000

Data Index: 86762 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.5690. Min Act: -0.0000

Data Index: 1685423 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.4196. Min Act: -0.0000

Data Index: 220503 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1249053 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.3779. Min Act: -0.0000

Data Index: 904968 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.6000. Min Act: -0.0000

Data Index: 1583564 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1978997 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.4035. Min Act: -0.0000

Data Index: 181078 (The Pile)

Max Activating Token Index: 655

Text #8

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1785781 (The Pile)

Max Activating Token Index: 803

Text #9

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1951411 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.4330. Min Act: -0.0000

Data Index: 770636 (The Pile)

Max Activating Token Index: 476

Text #11

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.4440. Min Act: -0.0000

Data Index: 823992 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1700145 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1442284 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2601. Min Act: -0.0000

Data Index: 475220 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2288. Min Act: -0.0000

Data Index: 460526 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2913. Min Act: -0.0000

Data Index: 1418263 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2784. Min Act: -0.0000

Data Index: 34548 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2679. Min Act: -0.0000

Data Index: 990144 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 1.6000. Min Range: -1.6000

Max Act: 1.2601. Min Act: -0.0000

Data Index: 208281 (The Pile)

Max Activating Token Index: 77