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

Dataset: The Pile

Neuron 3210 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: 1.0382. Min Range: -1.0382

Max Act: 0.9968. Min Act: -0.0000

Data Index: 773886 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8970. Min Act: -0.0000

Data Index: 655181 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9182. Min Act: -0.0000

Data Index: 454694 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9325. Min Act: -0.0000

Data Index: 856948 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1125839 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8816. Min Act: -0.0000

Data Index: 537377 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9596. Min Act: -0.0000

Data Index: 386380 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 1.0382. Min Range: -1.0382

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1217068 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9916. Min Act: -0.0000

Data Index: 514784 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9632. Min Act: -0.0000

Data Index: 686735 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9237. Min Act: -0.0000

Data Index: 491823 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8913. Min Act: -0.0000

Data Index: 985282 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 1.0382. Min Range: -1.0382

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1061434 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1511335 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8999. Min Act: -0.0000

Data Index: 435353 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9286. Min Act: -0.0000

Data Index: 875410 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1827553 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1994352 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8707. Min Act: -0.0000

Data Index: 456000 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8690. Min Act: -0.0000

Data Index: 778641 (The Pile)

Max Activating Token Index: 622