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

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

Neuron 1548 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.6787. Min Act: -0.0000

Data Index: 751406 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.6222. Min Act: -0.0000

Data Index: 556741 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.6355. Min Act: -0.0000

Data Index: 433776 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5884. Min Act: -0.0000

Data Index: 28300 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5726. Min Act: -0.0000

Data Index: 594639 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1174760 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1051638 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1031430 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5798. Min Act: -0.0001

Data Index: 634046 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1069789 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5505. Min Act: -0.0000

Data Index: 690391 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5508. Min Act: -0.0001

Data Index: 980397 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5611. Min Act: -0.0000

Data Index: 815094 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5184. Min Act: -0.0001

Data Index: 862531 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5347. Min Act: -0.0001

Data Index: 277427 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1338114 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5291. Min Act: -0.0000

Data Index: 128022 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1135897 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5453. Min Act: -0.0001

Data Index: 17610 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5073. Min Act: -0.0001

Data Index: 1082425 (C4 (Web Text))

Max Activating Token Index: 667