Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1849 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1732. Min Act: -0.0003

Data Index: 627943 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1627. Min Act: -0.0003

Data Index: 719007 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1464. Min Act: -0.0003

Data Index: 1156046 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1382. Min Act: -0.0003

Data Index: 87757 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1394. Min Act: -0.0003

Data Index: 416848 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1451. Min Act: -0.0003

Data Index: 1170252 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1342. Min Act: -0.0003

Data Index: 548038 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1174. Min Act: -0.0003

Data Index: 1018781 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1187. Min Act: -0.0003

Data Index: 919885 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1222. Min Act: -0.0003

Data Index: 869262 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1197. Min Act: -0.0003

Data Index: 214524 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1143. Min Act: -0.0003

Data Index: 15784 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1239. Min Act: -0.0003

Data Index: 715656 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1189. Min Act: -0.0003

Data Index: 554690 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1125. Min Act: -0.0003

Data Index: 271043 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1001. Min Act: -0.0003

Data Index: 77293 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1120. Min Act: -0.0003

Data Index: 207625 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1104. Min Act: -0.0003

Data Index: 556510 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1142. Min Act: -0.0003

Data Index: 98575 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1139. Min Act: -0.0003

Data Index: 556395 (C4 (Web Text))

Max Activating Token Index: 125