Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2526 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0384. Min Range: -1.0384

Max Act: 1.0384. Min Act: -0.0000

Data Index: 636075 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9135. Min Act: -0.0000

Data Index: 989013 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8602. Min Act: -0.0000

Data Index: 366671 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8863. Min Act: -0.0000

Data Index: 601884 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8379. Min Act: -0.0000

Data Index: 569655 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7736. Min Act: -0.0000

Data Index: 630309 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8302. Min Act: -0.0000

Data Index: 814099 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9189. Min Act: -0.0000

Data Index: 896740 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8658. Min Act: -0.0000

Data Index: 798439 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1075474 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7999. Min Act: -0.0000

Data Index: 863702 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1017739 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1301216 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8128. Min Act: -0.0000

Data Index: 200495 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8288. Min Act: -0.0000

Data Index: 356591 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.6950. Min Act: -0.0000

Data Index: 187137 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7365. Min Act: -0.0000

Data Index: 464096 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7770. Min Act: -0.0000

Data Index: 485592 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1129324 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7120. Min Act: -0.0000

Data Index: 376893 (C4 (Web Text))

Max Activating Token Index: 132