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

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

Neuron 285 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 741860 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 826755 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 336309 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 303539 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 293240 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 893810 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 454150 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 957848 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 1213903 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 459042 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 261797 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 127514 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1139407 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 358920 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 536821 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 947025 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 904711 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 224386 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 402771 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 454834 (C4 (Web Text))

Max Activating Token Index: 554