Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 298 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4609. Min Act: -0.0001

Data Index: 3484 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4543. Min Act: -0.0001

Data Index: 1229371 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4342. Min Act: -0.0001

Data Index: 689840 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3870. Min Act: -0.0001

Data Index: 824551 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3856. Min Act: -0.0001

Data Index: 889572 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3860. Min Act: -0.0001

Data Index: 193004 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3962. Min Act: -0.0001

Data Index: 1014475 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3888. Min Act: -0.0001

Data Index: 1043702 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3641. Min Act: -0.0001

Data Index: 1232503 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3828. Min Act: -0.0001

Data Index: 886812 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3688. Min Act: -0.0001

Data Index: 1330940 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3641. Min Act: -0.0001

Data Index: 1149538 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3876. Min Act: -0.0001

Data Index: 565571 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3698. Min Act: -0.0001

Data Index: 346069 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3555. Min Act: -0.0001

Data Index: 1123327 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3543. Min Act: -0.0001

Data Index: 819659 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3388. Min Act: -0.0001

Data Index: 798820 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3611. Min Act: -0.0001

Data Index: 215553 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3481. Min Act: -0.0001

Data Index: 864999 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3509. Min Act: -0.0001

Data Index: 626865 (C4 (Web Text))

Max Activating Token Index: 538