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

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

Neuron 1377 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: 1.2429. Min Range: -1.2429

Max Act: 1.2429. Min Act: -0.0000

Data Index: 12388 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.1556. Min Act: -0.0000

Data Index: 1095250 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8846. Min Act: -0.0000

Data Index: 314707 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8587. Min Act: -0.0000

Data Index: 161451 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8581. Min Act: -0.0000

Data Index: 271425 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8528. Min Act: 0.0000

Data Index: 850532 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8327. Min Act: -0.0000

Data Index: 718263 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8206. Min Act: -0.0000

Data Index: 18197 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7887. Min Act: -0.0000

Data Index: 444777 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1289362 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7995. Min Act: -0.0000

Data Index: 167931 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1115176 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7345. Min Act: -0.0000

Data Index: 671600 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7509. Min Act: -0.0000

Data Index: 754555 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1031067 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7093. Min Act: -0.0000

Data Index: 468188 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7434. Min Act: -0.0000

Data Index: 999596 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7106. Min Act: -0.0000

Data Index: 161031 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7390. Min Act: -0.0000

Data Index: 948572 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.7300. Min Act: -0.0000

Data Index: 427800 (C4 (Web Text))

Max Activating Token Index: 609