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

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

Neuron 2841 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: 3.3386. Min Range: -3.3386

Max Act: 3.3386. Min Act: -0.0000

Data Index: 427322 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.4573. Min Act: -0.0000

Data Index: 812688 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.0094. Min Act: -0.0000

Data Index: 946998 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.0732. Min Act: -0.0000

Data Index: 157353 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.9538. Min Act: -0.0000

Data Index: 1320557 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.9218. Min Act: -0.0000

Data Index: 725540 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.9281. Min Act: -0.0000

Data Index: 1201477 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.9052. Min Act: -0.0000

Data Index: 1445366 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1262232 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.8773. Min Act: -0.0000

Data Index: 1154304 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.7246. Min Act: -0.0000

Data Index: 713807 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.7010. Min Act: -0.0000

Data Index: 602791 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.7441. Min Act: -0.0000

Data Index: 913951 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.6391. Min Act: -0.0000

Data Index: 254300 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.6251. Min Act: -0.0000

Data Index: 1593662 (Python Code)

Max Activating Token Index: 691

Text #15

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.6081. Min Act: -0.0000

Data Index: 763947 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.6885. Min Act: 0.0000

Data Index: 703892 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.5920. Min Act: -0.0000

Data Index: 894297 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.6736. Min Act: -0.0000

Data Index: 504998 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 3.3386. Min Range: -3.3386

Max Act: 1.6628. Min Act: -0.0000

Data Index: 461025 (C4 (Web Text))

Max Activating Token Index: 136