Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4534 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2450. Min Act: -0.0000

Data Index: 477093 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2138. Min Act: -0.0000

Data Index: 680264 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1277921 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1181287 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1878. Min Act: -0.0000

Data Index: 133488 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1727. Min Act: -0.0000

Data Index: 131280 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1625. Min Act: -0.0000

Data Index: 293109 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1086944 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1710. Min Act: -0.0000

Data Index: 235787 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1646. Min Act: -0.0000

Data Index: 527743 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1647. Min Act: -0.0000

Data Index: 237511 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1613. Min Act: -0.0000

Data Index: 499767 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1001322 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1298641 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1813. Min Act: -0.0000

Data Index: 867326 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1625. Min Act: -0.0000

Data Index: 307198 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1400. Min Act: -0.0000

Data Index: 323554 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1542. Min Act: -0.0000

Data Index: 249285 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1155118 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1310. Min Act: -0.0000

Data Index: 468811 (C4 (Web Text))

Max Activating Token Index: 594