Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3495 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6159. Min Act: -0.0000

Data Index: 333749 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7566. Min Act: -0.0000

Data Index: 417852 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6314. Min Act: -0.0000

Data Index: 314914 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.4860. Min Act: -0.0000

Data Index: 755748 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.3152. Min Act: -0.0000

Data Index: 843760 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.3771. Min Act: -0.0000

Data Index: 170653 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.3014. Min Act: -0.0000

Data Index: 630439 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.3045. Min Act: -0.0000

Data Index: 392840 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.3311. Min Act: -0.0000

Data Index: 1035524 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2997. Min Act: -0.0000

Data Index: 630320 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2671. Min Act: -0.0000

Data Index: 739076 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.1962. Min Act: -0.0000

Data Index: 767773 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2661. Min Act: -0.0000

Data Index: 1173922 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1156154 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2721. Min Act: -0.0000

Data Index: 270195 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2040. Min Act: -0.0000

Data Index: 220552 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.1294. Min Act: -0.0000

Data Index: 422793 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2881. Min Act: -0.0000

Data Index: 999843 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.1469. Min Act: -0.0000

Data Index: 480251 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1337895 (C4 (Web Text))

Max Activating Token Index: 130