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

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

Neuron 4706 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: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0002

Data Index: 740344 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0523. Min Act: -0.0002

Data Index: 237913 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0442. Min Act: -0.0002

Data Index: 387438 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0424. Min Act: -0.0002

Data Index: 138717 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0413. Min Act: -0.0002

Data Index: 162783 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0402. Min Act: -0.0002

Data Index: 991208 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0384. Min Act: -0.0002

Data Index: 589345 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1020683 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1140262 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1088082 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0416. Min Act: -0.0002

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1025153 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0367. Min Act: -0.0002

Data Index: 933000 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0361. Min Act: -0.0002

Data Index: 504971 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0404. Min Act: -0.0002

Data Index: 685111 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1054168 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0370. Min Act: -0.0002

Data Index: 200691 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0386. Min Act: -0.0002

Data Index: 297723 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0354. Min Act: -0.0002

Data Index: 819944 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1102760 (C4 (Web Text))

Max Activating Token Index: 872