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

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

Neuron 1614 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: 0.7805. Min Range: -0.7805

Max Act: 0.7805. Min Act: -0.0001

Data Index: 277470 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6686. Min Act: -0.0001

Data Index: 455196 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6816. Min Act: -0.0001

Data Index: 202621 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5460. Min Act: -0.0001

Data Index: 1122637 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5025. Min Act: -0.0001

Data Index: 575063 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4652. Min Act: -0.0001

Data Index: 960360 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4670. Min Act: -0.0002

Data Index: 260343 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3652. Min Act: -0.0001

Data Index: 34527 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4207. Min Act: -0.0001

Data Index: 600993 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4059. Min Act: -0.0001

Data Index: 1212056 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4732. Min Act: -0.0001

Data Index: 140720 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4415. Min Act: -0.0001

Data Index: 920535 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4288. Min Act: -0.0001

Data Index: 368773 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3930. Min Act: -0.0001

Data Index: 261687 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3994. Min Act: -0.0001

Data Index: 1175752 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4386. Min Act: -0.0001

Data Index: 585987 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4128. Min Act: -0.0001

Data Index: 844577 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4158. Min Act: -0.0001

Data Index: 1176357 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3954. Min Act: -0.0001

Data Index: 679051 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4008. Min Act: -0.0001

Data Index: 705767 (C4 (Web Text))

Max Activating Token Index: 889