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

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

Neuron 4438 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: 0.0553. Min Range: -0.0553

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1131194 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0553. Min Act: -0.0002

Data Index: 232887 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0403. Min Act: -0.0002

Data Index: 685096 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0394. Min Act: -0.0002

Data Index: 742277 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0410. Min Act: -0.0002

Data Index: 158053 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1239549 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1251481 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0390. Min Act: -0.0002

Data Index: 21811 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0409. Min Act: -0.0002

Data Index: 660315 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0366. Min Act: -0.0002

Data Index: 203990 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1154591 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1257639 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0352. Min Act: -0.0002

Data Index: 675455 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0362. Min Act: -0.0002

Data Index: 160868 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0349. Min Act: -0.0002

Data Index: 296266 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0370. Min Act: -0.0002

Data Index: 509561 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0326. Min Act: -0.0002

Data Index: 771970 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0311. Min Act: -0.0002

Data Index: 934818 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1093858 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1125693 (C4 (Web Text))

Max Activating Token Index: 929