Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 196 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 18544 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1483935 (Python Code)

Max Activating Token Index: 96

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0490. Min Act: -0.0002

Data Index: 284420 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0353. Min Act: -0.0002

Data Index: 677558 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0363. Min Act: -0.0002

Data Index: 70723 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0372. Min Act: -0.0002

Data Index: 820547 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1347461 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1051157 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0320. Min Act: -0.0002

Data Index: 566940 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0345. Min Act: -0.0002

Data Index: 301829 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0307. Min Act: -0.0002

Data Index: 485485 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0333. Min Act: -0.0002

Data Index: 243913 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0289. Min Act: -0.0002

Data Index: 579766 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0344. Min Act: -0.0002

Data Index: 897418 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0324. Min Act: -0.0002

Data Index: 719578 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0312. Min Act: -0.0002

Data Index: 580418 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0317. Min Act: -0.0002

Data Index: 946026 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1457718 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1041055 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1093786 (C4 (Web Text))

Max Activating Token Index: 170