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

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

Neuron 4936 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.5916. Min Act: -0.0000

Data Index: 87325 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.5833. Min Act: 0.0001

Data Index: 979383 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.5151. Min Act: -0.0000

Data Index: 582085 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.5290. Min Act: 0.0000

Data Index: 42573 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4663. Min Act: -0.0000

Data Index: 509361 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4845. Min Act: 0.0001

Data Index: 592399 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4549. Min Act: -0.0000

Data Index: 442391 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4804. Min Act: -0.0000

Data Index: 828296 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1146361 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1022633 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4420. Min Act: -0.0000

Data Index: 953013 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4473. Min Act: -0.0000

Data Index: 936782 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4447. Min Act: -0.0000

Data Index: 342328 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4616. Min Act: -0.0000

Data Index: 489866 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4512. Min Act: -0.0000

Data Index: 822576 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4208. Min Act: -0.0000

Data Index: 493174 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4253. Min Act: -0.0000

Data Index: 324360 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4221. Min Act: -0.0000

Data Index: 184190 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4203. Min Act: -0.0000

Data Index: 353860 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4320. Min Act: -0.0000

Data Index: 637488 (C4 (Web Text))

Max Activating Token Index: 573