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

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

Neuron 3103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.3344. Min Act: -0.0000

Data Index: 1054566 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.2126. Min Act: -0.0000

Data Index: 764152 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.4327. Min Act: -0.0000

Data Index: 682417 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.1807. Min Act: -0.0000

Data Index: 143411 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.0321. Min Act: -0.0000

Data Index: 314490 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.4755. Min Act: -0.0000

Data Index: 155393 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.0690. Min Act: -0.0000

Data Index: 1159743 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.9552. Min Act: -0.0000

Data Index: 187095 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.0794. Min Act: -0.0000

Data Index: 695724 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.9513. Min Act: -0.0000

Data Index: 47225 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.8316. Min Act: -0.0000

Data Index: 1011282 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 2.4755. Min Range: -2.4755

Max Act: 2.0428. Min Act: -0.0000

Data Index: 206617 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.9157. Min Act: -0.0000

Data Index: 480033 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.8072. Min Act: -0.0000

Data Index: 265945 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.7898. Min Act: -0.0000

Data Index: 529398 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.8298. Min Act: -0.0000

Data Index: 823332 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.8370. Min Act: -0.0000

Data Index: 197918 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.8308. Min Act: -0.0000

Data Index: 1244719 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.8330. Min Act: -0.0000

Data Index: 47289 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 2.4755. Min Range: -2.4755

Max Act: 1.8253. Min Act: -0.0000

Data Index: 1345273 (C4 (Web Text))

Max Activating Token Index: 192