Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 79 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1473723 (Python Code)

Max Activating Token Index: 729

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0498. Min Act: 0.0001

Data Index: 559958 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1382129 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0478. Min Act: -0.0002

Data Index: 865034 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1137659 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0433. Min Act: -0.0002

Data Index: 73891 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1637962 (Python Code)

Max Activating Token Index: 347

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0425. Min Act: -0.0002

Data Index: 345056 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0425. Min Act: -0.0003

Data Index: 783231 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0431. Min Act: -0.0003

Data Index: 179084 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0430. Min Act: -0.0000

Data Index: 886803 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0415. Min Act: -0.0003

Data Index: 38898 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1384974 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0422. Min Act: -0.0002

Data Index: 502494 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0418. Min Act: -0.0003

Data Index: 997264 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0422. Min Act: -0.0002

Data Index: 515671 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0417. Min Act: -0.0002

Data Index: 531756 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0413. Min Act: -0.0003

Data Index: 674999 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0413. Min Act: -0.0002

Data Index: 307595 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0403. Min Act: -0.0003

Data Index: 491432 (C4 (Web Text))

Max Activating Token Index: 135