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

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

Neuron 1005 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: 0.0558. Min Range: -0.0558

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1149895 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0003

Data Index: 481042 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1010412 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0449. Min Act: -0.0003

Data Index: 598663 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0450. Min Act: -0.0004

Data Index: 724315 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0444. Min Act: -0.0002

Data Index: 822564 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1308265 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0447. Min Act: -0.0003

Data Index: 110276 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0426. Min Act: -0.0003

Data Index: 988968 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0452. Min Act: -0.0002

Data Index: 196006 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0423. Min Act: -0.0003

Data Index: 979986 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0435. Min Act: -0.0003

Data Index: 126151 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0418. Min Act: -0.0003

Data Index: 167257 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0424. Min Act: -0.0003

Data Index: 752366 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1158203 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0431. Min Act: -0.0003

Data Index: 553539 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0424. Min Act: -0.0003

Data Index: 141574 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0417. Min Act: -0.0003

Data Index: 43111 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0414. Min Act: -0.0004

Data Index: 730717 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0414. Min Act: -0.0002

Data Index: 799715 (C4 (Web Text))

Max Activating Token Index: 350