Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2270 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.2181. Min Act: -0.0001

Data Index: 1055842 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0881. Min Act: -0.0001

Data Index: 483080 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0860. Min Act: -0.0001

Data Index: 896344 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.1138. Min Act: -0.0001

Data Index: 510771 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.1246. Min Act: -0.0001

Data Index: 607944 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0439. Min Act: -0.0001

Data Index: 610112 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0797. Min Act: -0.0001

Data Index: 677748 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0389. Min Act: -0.0001

Data Index: 77639 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0144. Min Act: -0.0001

Data Index: 561003 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0669. Min Act: -0.0001

Data Index: 982286 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0581. Min Act: -0.0001

Data Index: 482838 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0571. Min Act: -0.0001

Data Index: 1002545 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0515. Min Act: -0.0001

Data Index: 1280289 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0187. Min Act: -0.0001

Data Index: 569329 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.1221. Min Act: -0.0001

Data Index: 1016243 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0071. Min Act: -0.0001

Data Index: 1082961 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9525. Min Act: -0.0001

Data Index: 120177 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0705. Min Act: -0.0001

Data Index: 244449 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.1255. Min Act: -0.0001

Data Index: 392586 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0166. Min Act: -0.0001

Data Index: 1122229 (C4 (Web Text))

Max Activating Token Index: 997