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

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

Neuron 3042 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8419. Min Range: -5.8419

Max Act: 5.8419. Min Act: -0.0000

Data Index: 960657 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 5.8419. Min Range: -5.8419

Max Act: 5.1923. Min Act: -0.0000

Data Index: 453253 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 5.8419. Min Range: -5.8419

Max Act: 5.4973. Min Act: -0.0000

Data Index: 751703 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 5.8419. Min Range: -5.8419

Max Act: 5.0754. Min Act: -0.0000

Data Index: 590992 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 5.8419. Min Range: -5.8419

Max Act: 5.1270. Min Act: -0.0000

Data Index: 42343 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.6217. Min Act: -0.0000

Data Index: 181096 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.9446. Min Act: -0.0000

Data Index: 901411 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.8449. Min Act: -0.0000

Data Index: 845528 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.8360. Min Act: -0.0000

Data Index: 1091230 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.8153. Min Act: -0.0000

Data Index: 259343 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.7738. Min Act: -0.0000

Data Index: 881815 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.6404. Min Act: -0.0000

Data Index: 1146223 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.9655. Min Act: -0.0000

Data Index: 1072234 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.9384. Min Act: -0.0000

Data Index: 1288270 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.5699. Min Act: -0.0000

Data Index: 579858 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.3784. Min Act: -0.0000

Data Index: 1101787 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.5080. Min Act: -0.0000

Data Index: 797184 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.6874. Min Act: -0.0000

Data Index: 877137 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 5.8419. Min Range: -5.8419

Max Act: 3.9332. Min Act: -0.0000

Data Index: 359271 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 5.8419. Min Range: -5.8419

Max Act: 4.4479. Min Act: -0.0000

Data Index: 1024641 (C4 (Web Text))

Max Activating Token Index: 700