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

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

Neuron 3561 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.1463. Min Act: -0.0001

Data Index: 399809 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8085. Min Act: -0.0001

Data Index: 809529 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7328. Min Act: -0.0001

Data Index: 283881 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7520. Min Act: -0.0001

Data Index: 850033 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6931. Min Act: -0.0001

Data Index: 563510 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7110. Min Act: -0.0001

Data Index: 386904 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6720. Min Act: -0.0001

Data Index: 815316 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7072. Min Act: -0.0001

Data Index: 1274971 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6880. Min Act: -0.0001

Data Index: 439192 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7253. Min Act: -0.0001

Data Index: 1174182 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7250. Min Act: -0.0001

Data Index: 364139 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7016. Min Act: -0.0001

Data Index: 300677 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6605. Min Act: -0.0001

Data Index: 678619 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1110996 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6546. Min Act: -0.0001

Data Index: 138519 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7137. Min Act: -0.0001

Data Index: 953743 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6271. Min Act: -0.0001

Data Index: 374369 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1034740 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6626. Min Act: -0.0001

Data Index: 83338 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6812. Min Act: -0.0001

Data Index: 303011 (C4 (Web Text))

Max Activating Token Index: 797