Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1831 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6215. Min Act: -0.0001

Data Index: 352505 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5716. Min Act: -0.0001

Data Index: 292891 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5735. Min Act: -0.0001

Data Index: 881985 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5705. Min Act: -0.0001

Data Index: 153028 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5746. Min Act: -0.0001

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5666. Min Act: -0.0001

Data Index: 755304 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5423. Min Act: -0.0001

Data Index: 430957 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5366. Min Act: -0.0001

Data Index: 323448 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4962. Min Act: -0.0001

Data Index: 1151330 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5567. Min Act: -0.0001

Data Index: 554954 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5478. Min Act: -0.0001

Data Index: 133253 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5094. Min Act: -0.0001

Data Index: 451055 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5101. Min Act: -0.0001

Data Index: 598498 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5374. Min Act: -0.0001

Data Index: 1311435 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4814. Min Act: -0.0001

Data Index: 1009204 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4756. Min Act: -0.0001

Data Index: 834636 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4873. Min Act: -0.0001

Data Index: 174183 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4534. Min Act: -0.0001

Data Index: 266283 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4934. Min Act: -0.0001

Data Index: 1346750 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5080. Min Act: -0.0001

Data Index: 817386 (C4 (Web Text))

Max Activating Token Index: 219