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

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

Neuron 2515 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1787. Min Range: -1.1787

Max Act: 1.1208. Min Act: -0.0000

Data Index: 827830 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.1787. Min Range: -1.1787

Max Act: 1.1787. Min Act: -0.0000

Data Index: 118506 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8682. Min Act: -0.0000

Data Index: 368275 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1175010 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8405. Min Act: -0.0000

Data Index: 633465 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8419. Min Act: -0.0000

Data Index: 196 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8331. Min Act: -0.0000

Data Index: 117136 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1221241 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8442. Min Act: -0.0000

Data Index: 497903 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7839. Min Act: -0.0000

Data Index: 259940 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7045. Min Act: -0.0001

Data Index: 1071948 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7691. Min Act: -0.0000

Data Index: 107545 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1193266 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1276739 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1100289 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7716. Min Act: -0.0001

Data Index: 515912 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1252873 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.7262. Min Act: -0.0000

Data Index: 299443 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.6535. Min Act: -0.0000

Data Index: 303311 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.6768. Min Act: -0.0000

Data Index: 436164 (C4 (Web Text))

Max Activating Token Index: 272