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

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

Neuron 2227 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4024. Min Range: -2.4024

Max Act: 2.4024. Min Act: -0.0000

Data Index: 748982 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 2.4024. Min Range: -2.4024

Max Act: 2.1586. Min Act: -0.0000

Data Index: 1047228 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.6414. Min Act: 0.0000

Data Index: 945325 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.5250. Min Act: -0.0000

Data Index: 257904 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1194755 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.4849. Min Act: -0.0000

Data Index: 1192450 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.6707. Min Act: -0.0000

Data Index: 68935 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.6548. Min Act: -0.0000

Data Index: 1171581 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.7407. Min Act: -0.0000

Data Index: 123694 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.6315. Min Act: -0.0000

Data Index: 903229 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.6001. Min Act: -0.0000

Data Index: 369453 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1103022 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.6781. Min Act: -0.0000

Data Index: 912861 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.5294. Min Act: -0.0000

Data Index: 1250697 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.4064. Min Act: -0.0000

Data Index: 225144 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.4182. Min Act: -0.0000

Data Index: 614635 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.4040. Min Act: -0.0000

Data Index: 131766 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.4753. Min Act: -0.0000

Data Index: 161583 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1318812 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 2.4024. Min Range: -2.4024

Max Act: 1.4772. Min Act: -0.0000

Data Index: 599358 (C4 (Web Text))

Max Activating Token Index: 317