Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3547 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2886. Min Range: -3.2886

Max Act: 3.2886. Min Act: -0.0000

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 3.2886. Min Range: -3.2886

Max Act: 3.2149. Min Act: -0.0000

Data Index: 282894 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.8131. Min Act: -0.0000

Data Index: 1408376 (Python Code)

Max Activating Token Index: 640

Text #3

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.8158. Min Act: -0.0000

Data Index: 229606 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 3.2886. Min Range: -3.2886

Max Act: 3.0455. Min Act: -0.0000

Data Index: 915813 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.9406. Min Act: -0.0000

Data Index: 667261 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.8438. Min Act: -0.0000

Data Index: 412227 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.6320. Min Act: -0.0000

Data Index: 1619575 (Python Code)

Max Activating Token Index: 969

Text #8

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.4898. Min Act: -0.0000

Data Index: 152696 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.7119. Min Act: -0.0000

Data Index: 134812 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.4375. Min Act: -0.0000

Data Index: 903892 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.4310. Min Act: -0.0000

Data Index: 219665 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.3887. Min Act: -0.0000

Data Index: 1072928 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.6353. Min Act: -0.0000

Data Index: 285342 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.4825. Min Act: -0.0000

Data Index: 1139593 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.6180. Min Act: -0.0000

Data Index: 349267 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.3540. Min Act: -0.0000

Data Index: 1394181 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.4642. Min Act: -0.0000

Data Index: 534078 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.3204. Min Act: -0.0000

Data Index: 1548409 (Python Code)

Max Activating Token Index: 260

Text #19

Max Range: 3.2886. Min Range: -3.2886

Max Act: 2.4369. Min Act: -0.0000

Data Index: 1073719 (C4 (Web Text))

Max Activating Token Index: 51