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

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

Neuron 3691 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4742. Min Act: -0.0002

Data Index: 1577961 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4809. Min Act: -0.0002

Data Index: 1473309 (Python Code)

Max Activating Token Index: 608

Text #2

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4628. Min Act: -0.0002

Data Index: 1499666 (Python Code)

Max Activating Token Index: 335

Text #3

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4717. Min Act: -0.0002

Data Index: 1589749 (Python Code)

Max Activating Token Index: 285

Text #4

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4315. Min Act: -0.0002

Data Index: 1363100 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4357. Min Act: -0.0002

Data Index: 1467794 (Python Code)

Max Activating Token Index: 354

Text #6

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3933. Min Act: -0.0002

Data Index: 1382255 (Python Code)

Max Activating Token Index: 780

Text #7

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4781. Min Act: -0.0002

Data Index: 1374015 (Python Code)

Max Activating Token Index: 277

Text #8

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4193. Min Act: -0.0002

Data Index: 1617930 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3983. Min Act: -0.0002

Data Index: 1431941 (Python Code)

Max Activating Token Index: 184

Text #10

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3972. Min Act: -0.0002

Data Index: 1492068 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3718. Min Act: -0.0002

Data Index: 1548453 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4063. Min Act: -0.0002

Data Index: 1590512 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4042. Min Act: -0.0002

Data Index: 1512197 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3929. Min Act: -0.0002

Data Index: 1429785 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3915. Min Act: -0.0002

Data Index: 1598858 (Python Code)

Max Activating Token Index: 242

Text #16

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3757. Min Act: -0.0002

Data Index: 1513659 (Python Code)

Max Activating Token Index: 440

Text #17

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3973. Min Act: -0.0002

Data Index: 1450481 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3692. Min Act: -0.0002

Data Index: 1513306 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3922. Min Act: -0.0002

Data Index: 1618278 (Python Code)

Max Activating Token Index: 523