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

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

Neuron 4090 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: 0.3823. Min Range: -0.3823

Max Act: 0.3823. Min Act: -0.0000

Data Index: 36336 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1175215 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3581. Min Act: -0.0000

Data Index: 779432 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1123853 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1292491 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1197949 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3515. Min Act: -0.0000

Data Index: 62433 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3269. Min Act: -0.0000

Data Index: 358535 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3157. Min Act: 0.0000

Data Index: 800077 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3194. Min Act: -0.0000

Data Index: 818670 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3230. Min Act: -0.0000

Data Index: 64349 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1337101 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1279396 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1332568 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3068. Min Act: -0.0000

Data Index: 647876 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3156. Min Act: -0.0000

Data Index: 343488 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1020543 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3382. Min Act: -0.0000

Data Index: 308596 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.3136. Min Act: -0.0000

Data Index: 912571 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.3823. Min Range: -0.3823

Max Act: 0.2834. Min Act: -0.0000

Data Index: 310517 (C4 (Web Text))

Max Activating Token Index: 790