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

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

Neuron 3572 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: 1.0916. Min Range: -1.0916

Max Act: 1.0916. Min Act: -0.0001

Data Index: 71234 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1060096 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.0916. Min Range: -1.0916

Max Act: 1.0042. Min Act: -0.0000

Data Index: 381122 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.9416. Min Act: -0.0001

Data Index: 805960 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8567. Min Act: -0.0000

Data Index: 394336 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7690. Min Act: -0.0001

Data Index: 264769 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.8384. Min Act: -0.0000

Data Index: 265319 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7890. Min Act: -0.0000

Data Index: 985721 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.6565. Min Act: -0.0001

Data Index: 311188 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1148706 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1182573 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7157. Min Act: -0.0000

Data Index: 569055 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.6975. Min Act: -0.0000

Data Index: 273037 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.5950. Min Act: -0.0001

Data Index: 361873 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.6599. Min Act: -0.0001

Data Index: 30886 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1258416 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.6404. Min Act: -0.0001

Data Index: 284493 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.6454. Min Act: -0.0000

Data Index: 530501 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.7119. Min Act: -0.0001

Data Index: 700994 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.0916. Min Range: -1.0916

Max Act: 0.6997. Min Act: -0.0001

Data Index: 799393 (C4 (Web Text))

Max Activating Token Index: 293