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

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

Neuron 2050 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0002

Data Index: 46028 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0540. Min Act: -0.0002

Data Index: 934602 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0457. Min Act: -0.0002

Data Index: 876477 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1324495 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0504. Min Act: -0.0002

Data Index: 622573 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1648506 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0449. Min Act: -0.0002

Data Index: 123243 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1586258 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0430. Min Act: -0.0002

Data Index: 959960 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0398. Min Act: -0.0002

Data Index: 496754 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0396. Min Act: -0.0002

Data Index: 794500 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1636388 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0424. Min Act: -0.0002

Data Index: 197029 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0393. Min Act: -0.0002

Data Index: 66744 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0388. Min Act: -0.0002

Data Index: 308426 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1387257 (Python Code)

Max Activating Token Index: 288

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0404. Min Act: -0.0002

Data Index: 826624 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0403. Min Act: -0.0002

Data Index: 514145 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0402. Min Act: -0.0002

Data Index: 147841 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1071320 (C4 (Web Text))

Max Activating Token Index: 853