Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 261 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.2253. Min Act: -0.0003

Data Index: 254861 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7133. Min Act: -0.0003

Data Index: 373615 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8990. Min Act: -0.0003

Data Index: 220305 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0511. Min Act: -0.0003

Data Index: 538053 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8493. Min Act: -0.0003

Data Index: 1177450 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8679. Min Act: -0.0003

Data Index: 158880 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7672. Min Act: -0.0003

Data Index: 999901 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8932. Min Act: -0.0003

Data Index: 1225609 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7895. Min Act: -0.0003

Data Index: 81792 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8558. Min Act: -0.0003

Data Index: 1096876 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8339. Min Act: -0.0003

Data Index: 189589 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8248. Min Act: -0.0003

Data Index: 323471 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8439. Min Act: -0.0003

Data Index: 674572 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.5834. Min Act: -0.0003

Data Index: 837826 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7874. Min Act: -0.0003

Data Index: 732602 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8324. Min Act: -0.0003

Data Index: 227027 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8020. Min Act: -0.0003

Data Index: 38448 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.6584. Min Act: -0.0003

Data Index: 736758 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7680. Min Act: -0.0003

Data Index: 909252 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8451. Min Act: -0.0003

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 424