Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 583 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9939. Min Act: -0.0001

Data Index: 1139876 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1160286 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.9261. Min Act: -0.0000

Data Index: 989330 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1309255 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.7709. Min Act: -0.0001

Data Index: 95705 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.7558. Min Act: -0.0000

Data Index: 432543 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.7259. Min Act: -0.0000

Data Index: 284127 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1199478 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6954. Min Act: -0.0001

Data Index: 386529 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6831. Min Act: -0.0000

Data Index: 620834 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6889. Min Act: -0.0000

Data Index: 639119 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6887. Min Act: -0.0001

Data Index: 1350742 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6146. Min Act: -0.0000

Data Index: 505694 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6093. Min Act: -0.0000

Data Index: 418406 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.5892. Min Act: -0.0000

Data Index: 197495 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6322. Min Act: -0.0001

Data Index: 1258818 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6447. Min Act: -0.0001

Data Index: 437357 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6595. Min Act: -0.0001

Data Index: 58868 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6084. Min Act: -0.0001

Data Index: 638395 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.9939. Min Range: -0.9939

Max Act: 0.6228. Min Act: -0.0001

Data Index: 817491 (C4 (Web Text))

Max Activating Token Index: 352