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

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

Neuron 4776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0126. Min Range: -3.0126

Max Act: 3.0126. Min Act: -0.0000

Data Index: 1312521 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.9019. Min Act: -0.0000

Data Index: 260011 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.8683. Min Act: -0.0000

Data Index: 186253 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.7238. Min Act: -0.0000

Data Index: 1121407 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.6829. Min Act: -0.0000

Data Index: 318795 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.5684. Min Act: -0.0000

Data Index: 556601 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.3381. Min Act: -0.0000

Data Index: 650601 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.4323. Min Act: -0.0000

Data Index: 462216 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.5609. Min Act: -0.0000

Data Index: 1277978 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.3896. Min Act: -0.0000

Data Index: 1030485 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.5059. Min Act: -0.0000

Data Index: 868104 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.3457. Min Act: -0.0000

Data Index: 446178 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.1851. Min Act: -0.0000

Data Index: 233416 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.2969. Min Act: -0.0000

Data Index: 831603 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.2744. Min Act: -0.0000

Data Index: 1116095 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.2609. Min Act: -0.0000

Data Index: 352290 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.1922. Min Act: -0.0000

Data Index: 954540 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.4075. Min Act: -0.0000

Data Index: 764551 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.3013. Min Act: -0.0000

Data Index: 827690 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 3.0126. Min Range: -3.0126

Max Act: 2.0311. Min Act: -0.0000

Data Index: 503564 (C4 (Web Text))

Max Activating Token Index: 840