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

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

Neuron 2072 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: 2.0275. Min Range: -2.0275

Max Act: 1.9672. Min Act: -0.0000

Data Index: 1021408 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.9322. Min Act: -0.0000

Data Index: 810296 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 2.0275. Min Range: -2.0275

Max Act: 2.0275. Min Act: -0.0000

Data Index: 694768 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.8207. Min Act: -0.0000

Data Index: 770387 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.7238. Min Act: -0.0000

Data Index: 460840 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.7135. Min Act: -0.0000

Data Index: 858230 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1169961 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.6640. Min Act: -0.0000

Data Index: 953310 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.6680. Min Act: -0.0000

Data Index: 770544 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.5320. Min Act: -0.0000

Data Index: 481074 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.6050. Min Act: -0.0000

Data Index: 1315341 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.4516. Min Act: -0.0000

Data Index: 956627 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.4577. Min Act: -0.0000

Data Index: 744971 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.6526. Min Act: -0.0000

Data Index: 710309 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1146433 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.5435. Min Act: -0.0000

Data Index: 462490 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1201908 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.5439. Min Act: -0.0000

Data Index: 183445 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.5057. Min Act: -0.0000

Data Index: 459829 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 2.0275. Min Range: -2.0275

Max Act: 1.5879. Min Act: -0.0000

Data Index: 469930 (C4 (Web Text))

Max Activating Token Index: 794