Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4897 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.9816. Min Act: -0.0000

Data Index: 774768 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.9427. Min Act: 0.0000

Data Index: 1276215 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.9585. Min Act: -0.0000

Data Index: 976818 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1248835 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1353645 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.8226. Min Act: -0.0000

Data Index: 644007 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.8432. Min Act: -0.0000

Data Index: 831559 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1221132 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1242227 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.8186. Min Act: -0.0000

Data Index: 148291 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.7684. Min Act: -0.0000

Data Index: 607350 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.8073. Min Act: -0.0000

Data Index: 345267 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.7737. Min Act: 0.0001

Data Index: 969640 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.7853. Min Act: -0.0000

Data Index: 653009 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.7573. Min Act: 0.0000

Data Index: 636168 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1030675 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.7984. Min Act: -0.0000

Data Index: 609098 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.7910. Min Act: 0.0000

Data Index: 445708 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1166684 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.9816. Min Range: -0.9816

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1251243 (C4 (Web Text))

Max Activating Token Index: 507