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

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

Neuron 4808 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.4288. Min Act: -0.0000

Data Index: 294783 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.4770. Min Act: -0.0000

Data Index: 655283 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1208946 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1390540 (Python Code)

Max Activating Token Index: 764

Text #4

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1580455 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1188681 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1378620 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.4503. Min Act: -0.0000

Data Index: 617544 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.2151. Min Act: -0.0000

Data Index: 777206 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.1997. Min Act: -0.0000

Data Index: 725294 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1339539 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1638826 (Python Code)

Max Activating Token Index: 257

Text #12

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1605247 (Python Code)

Max Activating Token Index: 522

Text #13

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.3595. Min Act: -0.0000

Data Index: 1487319 (Python Code)

Max Activating Token Index: 288

Text #14

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1059236 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.2383. Min Act: -0.0000

Data Index: 425505 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1515177 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.2885. Min Act: -0.0000

Data Index: 852013 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.2478. Min Act: -0.0000

Data Index: 741141 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.4791. Min Range: -1.4791

Max Act: 1.4160. Min Act: -0.0000

Data Index: 1647561 (Python Code)

Max Activating Token Index: 377