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

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

Neuron 4073 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1064061 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0952. Min Act: -0.0000

Data Index: 489472 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1611. Min Act: -0.0000

Data Index: 180274 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1301166 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1543. Min Act: -0.0000

Data Index: 184335 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0811. Min Act: -0.0000

Data Index: 163408 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1206. Min Act: -0.0000

Data Index: 179808 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.9646. Min Act: -0.0000

Data Index: 997542 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0840. Min Act: -0.0000

Data Index: 1401289 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1357658 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0895. Min Act: -0.0000

Data Index: 404987 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1696. Min Act: -0.0000

Data Index: 221600 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1333314 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0713. Min Act: -0.0000

Data Index: 221052 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.9143. Min Act: -0.0000

Data Index: 819095 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0705. Min Act: -0.0000

Data Index: 849640 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.9920. Min Act: -0.0000

Data Index: 535573 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0970. Min Act: -0.0000

Data Index: 584791 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1558985 (Python Code)

Max Activating Token Index: 519

Text #19

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1093. Min Act: -0.0000

Data Index: 952000 (C4 (Web Text))

Max Activating Token Index: 596