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

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

Neuron 2641 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0119. Min Range: -1.0119

Max Act: 1.0119. Min Act: -0.0001

Data Index: 452777 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9021. Min Act: -0.0001

Data Index: 1181877 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8984. Min Act: -0.0001

Data Index: 649104 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8876. Min Act: -0.0001

Data Index: 883668 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8643. Min Act: -0.0001

Data Index: 1153932 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8430. Min Act: -0.0001

Data Index: 534091 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8026. Min Act: -0.0001

Data Index: 1300066 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7166. Min Act: -0.0001

Data Index: 1347382 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8630. Min Act: -0.0001

Data Index: 970416 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7654. Min Act: -0.0001

Data Index: 291901 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8153. Min Act: -0.0001

Data Index: 1165913 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8338. Min Act: -0.0001

Data Index: 418013 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8671. Min Act: -0.0001

Data Index: 87477 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7873. Min Act: -0.0001

Data Index: 307804 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8142. Min Act: -0.0001

Data Index: 1243064 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8012. Min Act: -0.0001

Data Index: 298294 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7756. Min Act: -0.0001

Data Index: 208265 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7629. Min Act: -0.0001

Data Index: 919294 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7405. Min Act: -0.0001

Data Index: 972772 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.6618. Min Act: -0.0001

Data Index: 646763 (C4 (Web Text))

Max Activating Token Index: 284