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

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

Neuron 1988 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0001

Data Index: 168744 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0692. Min Act: -0.0001

Data Index: 770874 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1281004 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0559. Min Act: -0.0001

Data Index: 941048 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0674. Min Act: -0.0001

Data Index: 233117 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0626. Min Act: -0.0001

Data Index: 325191 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0622. Min Act: -0.0001

Data Index: 854003 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0610. Min Act: -0.0002

Data Index: 596901 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0574. Min Act: -0.0001

Data Index: 396448 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1216964 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0684. Min Act: -0.0001

Data Index: 165765 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0550. Min Act: -0.0001

Data Index: 279694 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0615. Min Act: -0.0001

Data Index: 220112 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0646. Min Act: -0.0001

Data Index: 5003 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1328888 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0587. Min Act: -0.0001

Data Index: 211916 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1212966 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0607. Min Act: -0.0001

Data Index: 50418 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1215805 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0555. Min Act: -0.0001

Data Index: 815658 (C4 (Web Text))

Max Activating Token Index: 678