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

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

Neuron 1366 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: 0.8542. Min Range: -0.8542

Max Act: 0.8134. Min Act: -0.0003

Data Index: 75101 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7365. Min Act: -0.0003

Data Index: 679638 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7500. Min Act: -0.0004

Data Index: 832482 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7850. Min Act: -0.0003

Data Index: 272477 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.8312. Min Act: -0.0003

Data Index: 1271607 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7778. Min Act: -0.0003

Data Index: 535825 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7944. Min Act: -0.0003

Data Index: 95461 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6922. Min Act: -0.0003

Data Index: 88611 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.8082. Min Act: -0.0003

Data Index: 1188439 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7341. Min Act: -0.0003

Data Index: 1263377 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6919. Min Act: -0.0003

Data Index: 17823 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6898. Min Act: -0.0003

Data Index: 814024 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6040. Min Act: -0.0003

Data Index: 92675 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.5799. Min Act: -0.0003

Data Index: 1136975 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.8542. Min Act: -0.0003

Data Index: 878654 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6369. Min Act: -0.0003

Data Index: 97550 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.8219. Min Act: -0.0003

Data Index: 857447 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6547. Min Act: -0.0003

Data Index: 53183 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7612. Min Act: -0.0003

Data Index: 95806 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6234. Min Act: -0.0003

Data Index: 446448 (C4 (Web Text))

Max Activating Token Index: 655