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

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

Neuron 2053 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: 3.4712. Min Range: -3.4712

Max Act: 3.4712. Min Act: -0.0000

Data Index: 1297338 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 3.4712. Min Range: -3.4712

Max Act: 3.3941. Min Act: -0.0000

Data Index: 1253495 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7013. Min Act: -0.0000

Data Index: 230169 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.4712. Min Range: -3.4712

Max Act: 3.0919. Min Act: -0.0000

Data Index: 634295 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.6485. Min Act: -0.0000

Data Index: 436927 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.9316. Min Act: -0.0000

Data Index: 9713 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.8789. Min Act: -0.0000

Data Index: 733395 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7436. Min Act: -0.0000

Data Index: 651582 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.9937. Min Act: -0.0000

Data Index: 659786 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.8151. Min Act: -0.0000

Data Index: 468062 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.6625. Min Act: -0.0000

Data Index: 336550 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.6469. Min Act: -0.0000

Data Index: 835173 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7487. Min Act: -0.0000

Data Index: 289428 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.8144. Min Act: -0.0000

Data Index: 90859 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.6634. Min Act: -0.0000

Data Index: 509201 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.5915. Min Act: -0.0000

Data Index: 732290 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7468. Min Act: -0.0000

Data Index: 834628 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.4618. Min Act: -0.0000

Data Index: 1323174 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.6926. Min Act: -0.0000

Data Index: 1036430 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.5399. Min Act: -0.0000

Data Index: 738272 (C4 (Web Text))

Max Activating Token Index: 675