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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6381. Min Range: -3.6381

Max Act: 3.6381. Min Act: -0.0001

Data Index: 401400 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 3.6381. Min Range: -3.6381

Max Act: 3.6041. Min Act: -0.0001

Data Index: 1022604 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.6381. Min Range: -3.6381

Max Act: 3.4424. Min Act: -0.0000

Data Index: 432278 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 3.6381. Min Range: -3.6381

Max Act: 3.0516. Min Act: -0.0000

Data Index: 1024583 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.9066. Min Act: -0.0001

Data Index: 586252 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.8662. Min Act: -0.0000

Data Index: 876371 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 3.6381. Min Range: -3.6381

Max Act: 3.0128. Min Act: -0.0001

Data Index: 397309 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.8886. Min Act: -0.0000

Data Index: 575248 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.8607. Min Act: -0.0000

Data Index: 394161 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.8548. Min Act: -0.0001

Data Index: 84213 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.8391. Min Act: -0.0000

Data Index: 1304963 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.5654. Min Act: -0.0000

Data Index: 68234 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.5206. Min Act: -0.0000

Data Index: 455226 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.7710. Min Act: -0.0001

Data Index: 620427 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.6245. Min Act: -0.0000

Data Index: 960422 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.5045. Min Act: -0.0001

Data Index: 32059 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.7402. Min Act: -0.0001

Data Index: 139335 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.4644. Min Act: -0.0000

Data Index: 1345997 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.6703. Min Act: -0.0000

Data Index: 1088678 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 3.6381. Min Range: -3.6381

Max Act: 2.7685. Min Act: -0.0001

Data Index: 1284575 (C4 (Web Text))

Max Activating Token Index: 702