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

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

Neuron 152 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0006

Data Index: 217721 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0394. Min Act: -0.0006

Data Index: 196015 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0398. Min Act: -0.0006

Data Index: 1073042 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0384. Min Act: -0.0006

Data Index: 515539 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1130175 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0369. Min Act: -0.0006

Data Index: 192877 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1125611 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0372. Min Act: -0.0006

Data Index: 1141737 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0369. Min Act: -0.0006

Data Index: 734782 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0367. Min Act: -0.0006

Data Index: 524715 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0342. Min Act: -0.0006

Data Index: 302682 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0367. Min Act: -0.0006

Data Index: 470676 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0371. Min Act: -0.0006

Data Index: 139871 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0364. Min Act: -0.0006

Data Index: 1225010 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0353. Min Act: -0.0006

Data Index: 1341272 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0361. Min Act: -0.0006

Data Index: 884873 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0368. Min Act: -0.0006

Data Index: 159927 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1304186 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0344. Min Act: -0.0006

Data Index: 333658 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0352. Min Act: -0.0006

Data Index: 796130 (C4 (Web Text))

Max Activating Token Index: 62