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

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

Neuron 2583 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.7673. Min Act: -0.0002

Data Index: 1261677 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.6155. Min Act: -0.0002

Data Index: 1177353 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5555. Min Act: -0.0002

Data Index: 118932 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5830. Min Act: -0.0002

Data Index: 947556 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5377. Min Act: -0.0002

Data Index: 28557 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5479. Min Act: -0.0002

Data Index: 311959 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5283. Min Act: -0.0002

Data Index: 1064539 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5000. Min Act: -0.0002

Data Index: 766018 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5555. Min Act: -0.0002

Data Index: 804895 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5514. Min Act: -0.0002

Data Index: 227673 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5824. Min Act: -0.0002

Data Index: 888266 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5281. Min Act: -0.0003

Data Index: 506333 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.5358. Min Act: -0.0002

Data Index: 371660 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.4893. Min Act: -0.0002

Data Index: 1079075 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.4903. Min Act: -0.0002

Data Index: 509057 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.4992. Min Act: -0.0002

Data Index: 257283 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.4912. Min Act: -0.0002

Data Index: 714264 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.4711. Min Act: -0.0002

Data Index: 1225768 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.4838. Min Act: -0.0002

Data Index: 1298424 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.7673. Min Range: -1.7673

Max Act: 1.4984. Min Act: -0.0002

Data Index: 1248496 (C4 (Web Text))

Max Activating Token Index: 944