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

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

Neuron 1902 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6916. Min Act: -0.0003

Data Index: 693679 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5300. Min Act: -0.0003

Data Index: 232932 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5572. Min Act: -0.0003

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5870. Min Act: -0.0003

Data Index: 799709 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5458. Min Act: -0.0003

Data Index: 158263 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5765. Min Act: -0.0003

Data Index: 816699 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5394. Min Act: -0.0003

Data Index: 627231 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5542. Min Act: -0.0003

Data Index: 104844 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5336. Min Act: -0.0003

Data Index: 266776 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5678. Min Act: -0.0003

Data Index: 593263 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5640. Min Act: -0.0004

Data Index: 958633 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5415. Min Act: -0.0003

Data Index: 966601 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5578. Min Act: -0.0003

Data Index: 832908 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4989. Min Act: -0.0003

Data Index: 253896 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5490. Min Act: -0.0003

Data Index: 248487 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5514. Min Act: -0.0003

Data Index: 654174 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5130. Min Act: -0.0003

Data Index: 673963 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5470. Min Act: -0.0003

Data Index: 237682 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4918. Min Act: -0.0003

Data Index: 261931 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5437. Min Act: -0.0003

Data Index: 47335 (C4 (Web Text))

Max Activating Token Index: 51