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

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

Neuron 4123 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.7723. Min Act: -0.0000

Data Index: 129138 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.5651. Min Act: -0.0000

Data Index: 1014276 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.5148. Min Act: -0.0000

Data Index: 388117 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.4423. Min Act: -0.0000

Data Index: 1008580 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.5591. Min Act: -0.0000

Data Index: 1215806 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.3934. Min Act: -0.0000

Data Index: 691157 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.4564. Min Act: -0.0000

Data Index: 713460 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.3447. Min Act: -0.0000

Data Index: 195376 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.4451. Min Act: -0.0000

Data Index: 55339 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1194800 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.1831. Min Act: -0.0000

Data Index: 1001153 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.1615. Min Act: -0.0000

Data Index: 677687 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.1470. Min Act: -0.0000

Data Index: 1124631 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 2.7723. Min Range: -2.7723

Max Act: 2.0428. Min Act: -0.0000

Data Index: 210975 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 2.7723. Min Range: -2.7723

Max Act: 1.8709. Min Act: -0.0000

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 2.7723. Min Range: -2.7723

Max Act: 1.9116. Min Act: -0.0000

Data Index: 871990 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 2.7723. Min Range: -2.7723

Max Act: 1.6407. Min Act: -0.0000

Data Index: 540318 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 2.7723. Min Range: -2.7723

Max Act: 1.6507. Min Act: -0.0000

Data Index: 1214446 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 2.7723. Min Range: -2.7723

Max Act: 1.6209. Min Act: -0.0000

Data Index: 707831 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 2.7723. Min Range: -2.7723

Max Act: 1.6998. Min Act: -0.0000

Data Index: 1332257 (C4 (Web Text))

Max Activating Token Index: 421