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

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

Neuron 1500 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: 0.2283. Min Range: -0.2283

Max Act: 0.2283. Min Act: -0.0001

Data Index: 874812 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.2142. Min Act: -0.0001

Data Index: 350855 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1161184 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1359171 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.2002. Min Act: -0.0000

Data Index: 181794 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1884. Min Act: -0.0001

Data Index: 653411 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1917. Min Act: -0.0001

Data Index: 489913 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1153385 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1663. Min Act: -0.0000

Data Index: 240654 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1630. Min Act: -0.0000

Data Index: 685640 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1581. Min Act: -0.0000

Data Index: 288284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1207700 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1739. Min Act: -0.0001

Data Index: 712504 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1668. Min Act: -0.0000

Data Index: 333442 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1193461 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1705. Min Act: -0.0000

Data Index: 79751 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1536. Min Act: -0.0000

Data Index: 297534 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1639. Min Act: -0.0000

Data Index: 475808 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1048124 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1623. Min Act: -0.0001

Data Index: 441364 (C4 (Web Text))

Max Activating Token Index: 579