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

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

Neuron 364 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: 0.0973. Min Range: -0.0973

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1252113 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0973. Min Act: -0.0000

Data Index: 654666 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1031239 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1384975 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0971. Min Act: -0.0001

Data Index: 739303 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0919. Min Act: -0.0000

Data Index: 810205 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0935. Min Act: -0.0001

Data Index: 929098 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1608716 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0827. Min Act: -0.0000

Data Index: 779877 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0887. Min Act: -0.0001

Data Index: 176703 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0878. Min Act: -0.0001

Data Index: 258656 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0815. Min Act: -0.0000

Data Index: 847188 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0815. Min Act: -0.0001

Data Index: 29124 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1049061 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0808. Min Act: -0.0001

Data Index: 910414 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1458162 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1113191 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0819. Min Act: -0.0001

Data Index: 597926 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1175058 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0757. Min Act: -0.0000

Data Index: 273532 (C4 (Web Text))

Max Activating Token Index: 840