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

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

Neuron 1712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.2116. Min Act: -0.0001

Data Index: 562218 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.2095. Min Act: -0.0001

Data Index: 569215 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1858. Min Act: -0.0001

Data Index: 616754 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1847. Min Act: -0.0001

Data Index: 779164 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1804. Min Act: -0.0001

Data Index: 30873 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1738. Min Act: -0.0001

Data Index: 441111 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1344747 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1663. Min Act: -0.0001

Data Index: 207674 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1531. Min Act: -0.0001

Data Index: 253821 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1656. Min Act: -0.0001

Data Index: 76492 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1587. Min Act: -0.0001

Data Index: 687291 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1616. Min Act: -0.0001

Data Index: 93713 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1668. Min Act: -0.0001

Data Index: 939913 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1670. Min Act: -0.0001

Data Index: 85430 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1669. Min Act: -0.0001

Data Index: 904066 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1713. Min Act: -0.0001

Data Index: 641691 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1710. Min Act: -0.0001

Data Index: 545981 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1661. Min Act: -0.0001

Data Index: 160145 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1655. Min Act: -0.0001

Data Index: 503397 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.2116. Min Range: -0.2116

Max Act: 0.1658. Min Act: -0.0001

Data Index: 792157 (C4 (Web Text))

Max Activating Token Index: 499