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

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

Neuron 5304 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1104. Min Range: -1.1104

Max Act: 1.1104. Min Act: -0.0000

Data Index: 150341 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 1.1104. Min Range: -1.1104

Max Act: 1.0176. Min Act: -0.0000

Data Index: 450376 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.1104. Min Range: -1.1104

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1082836 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1602579 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1419139 (Python Code)

Max Activating Token Index: 629

Text #5

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1526977 (Python Code)

Max Activating Token Index: 282

Text #6

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.8602. Min Act: -0.0000

Data Index: 26785 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.8837. Min Act: -0.0000

Data Index: 525508 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1511406 (Python Code)

Max Activating Token Index: 539

Text #9

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.8636. Min Act: -0.0000

Data Index: 70010 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.8059. Min Act: -0.0000

Data Index: 597547 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1648318 (Python Code)

Max Activating Token Index: 605

Text #12

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1548432 (Python Code)

Max Activating Token Index: 435

Text #13

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1599491 (Python Code)

Max Activating Token Index: 452

Text #14

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1122962 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.8146. Min Act: -0.0000

Data Index: 885576 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1540981 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1421818 (Python Code)

Max Activating Token Index: 871

Text #18

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.7730. Min Act: -0.0000

Data Index: 763630 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.1104. Min Range: -1.1104

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1555862 (Python Code)

Max Activating Token Index: 32