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

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

Neuron 6008 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3856. Min Range: -2.3856

Max Act: 2.3856. Min Act: -0.0000

Data Index: 1585599 (Python Code)

Max Activating Token Index: 226

Text #1

Max Range: 2.3856. Min Range: -2.3856

Max Act: 2.2951. Min Act: -0.0000

Data Index: 751704 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 2.3856. Min Range: -2.3856

Max Act: 2.0192. Min Act: -0.0000

Data Index: 885556 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.8091. Min Act: -0.0000

Data Index: 1145300 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.8916. Min Act: -0.0000

Data Index: 154101 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.7633. Min Act: -0.0000

Data Index: 454666 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.7564. Min Act: -0.0000

Data Index: 1549097 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.7507. Min Act: -0.0000

Data Index: 891873 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.8345. Min Act: -0.0000

Data Index: 1590664 (Python Code)

Max Activating Token Index: 731

Text #9

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.7862. Min Act: -0.0000

Data Index: 1291976 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6925. Min Act: -0.0000

Data Index: 381395 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5660. Min Act: -0.0000

Data Index: 1650848 (Python Code)

Max Activating Token Index: 605

Text #12

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5141. Min Act: -0.0000

Data Index: 693082 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6058. Min Act: -0.0000

Data Index: 126301 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6014. Min Act: -0.0000

Data Index: 129686 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6913. Min Act: -0.0000

Data Index: 1431225 (Python Code)

Max Activating Token Index: 335

Text #16

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5577. Min Act: -0.0000

Data Index: 832224 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5513. Min Act: -0.0000

Data Index: 107961 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.4429. Min Act: -0.0000

Data Index: 477488 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5048. Min Act: -0.0000

Data Index: 781053 (C4 (Web Text))

Max Activating Token Index: 244