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

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

Neuron 2742 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.4495. Min Act: -0.0000

Data Index: 389714 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.4190. Min Act: -0.0000

Data Index: 1195401 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.8143. Min Act: -0.0000

Data Index: 484416 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.8971. Min Act: -0.0000

Data Index: 839700 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.8650. Min Act: -0.0000

Data Index: 433179 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.8726. Min Act: -0.0000

Data Index: 570923 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.8435. Min Act: -0.0000

Data Index: 840301 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.9303. Min Act: -0.0000

Data Index: 386687 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.6447. Min Act: -0.0000

Data Index: 1308514 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.8686. Min Act: -0.0000

Data Index: 290273 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0184. Min Act: -0.0000

Data Index: 10744 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.6613. Min Act: -0.0000

Data Index: 982360 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.5899. Min Act: -0.0000

Data Index: 63497 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.7375. Min Act: -0.0000

Data Index: 556564 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.7337. Min Act: -0.0000

Data Index: 586948 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.5858. Min Act: -0.0000

Data Index: 1545068 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.5020. Min Act: 0.0000

Data Index: 508767 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.6145. Min Act: -0.0000

Data Index: 1057158 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.2638. Min Act: -0.0000

Data Index: 638590 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.4168. Min Act: -0.0000

Data Index: 882728 (C4 (Web Text))

Max Activating Token Index: 979