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

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

Neuron 1322 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7351. Min Range: -2.7351

Max Act: 2.7351. Min Act: -0.0000

Data Index: 960833 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 2.7351. Min Range: -2.7351

Max Act: 2.6458. Min Act: -0.0000

Data Index: 988102 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 2.7351. Min Range: -2.7351

Max Act: 2.5764. Min Act: -0.0000

Data Index: 577312 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.7351. Min Range: -2.7351

Max Act: 2.0626. Min Act: -0.0000

Data Index: 125684 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 2.7351. Min Range: -2.7351

Max Act: 2.2405. Min Act: -0.0000

Data Index: 1208528 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 2.7351. Min Range: -2.7351

Max Act: 2.0994. Min Act: -0.0000

Data Index: 856282 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 2.7351. Min Range: -2.7351

Max Act: 2.0413. Min Act: -0.0000

Data Index: 528571 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.7924. Min Act: -0.0000

Data Index: 1237176 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.9705. Min Act: -0.0000

Data Index: 974072 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.9443. Min Act: -0.0000

Data Index: 1067418 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 2.7351. Min Range: -2.7351

Max Act: 2.0214. Min Act: -0.0000

Data Index: 775568 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.9167. Min Act: -0.0000

Data Index: 384938 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.7878. Min Act: -0.0000

Data Index: 719167 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.8857. Min Act: -0.0000

Data Index: 1561801 (Python Code)

Max Activating Token Index: 696

Text #14

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.8120. Min Act: -0.0000

Data Index: 445730 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.8837. Min Act: -0.0000

Data Index: 1618815 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.6899. Min Act: -0.0000

Data Index: 576839 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.8282. Min Act: -0.0000

Data Index: 1425937 (Python Code)

Max Activating Token Index: 572

Text #18

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.6727. Min Act: -0.0000

Data Index: 1204881 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 2.7351. Min Range: -2.7351

Max Act: 1.8473. Min Act: -0.0000

Data Index: 1148718 (C4 (Web Text))

Max Activating Token Index: 218