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

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

Neuron 1538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5428. Min Act: -0.0000

Data Index: 546900 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5676. Min Act: -0.0000

Data Index: 20023 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5273. Min Act: -0.0000

Data Index: 552970 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5228. Min Act: -0.0001

Data Index: 1156245 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1233573 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5012. Min Act: -0.0000

Data Index: 86113 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.5179. Min Act: -0.0000

Data Index: 501909 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4746. Min Act: -0.0000

Data Index: 216480 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4492. Min Act: -0.0001

Data Index: 1188104 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4706. Min Act: -0.0001

Data Index: 843103 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4679. Min Act: -0.0001

Data Index: 239033 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4350. Min Act: -0.0001

Data Index: 432122 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4345. Min Act: -0.0001

Data Index: 572338 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1143102 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4430. Min Act: -0.0000

Data Index: 335585 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4559. Min Act: -0.0000

Data Index: 429939 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4360. Min Act: -0.0001

Data Index: 939474 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4363. Min Act: -0.0001

Data Index: 1243642 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4180. Min Act: -0.0001

Data Index: 717121 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.5676. Min Range: -0.5676

Max Act: 0.4187. Min Act: -0.0000

Data Index: 175235 (C4 (Web Text))

Max Activating Token Index: 271