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

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

Neuron 5854 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.3382. Min Act: -0.0000

Data Index: 638724 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 3.3382. Min Range: -3.3382

Max Act: 2.5201. Min Act: -0.0000

Data Index: 600982 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 3.3382. Min Range: -3.3382

Max Act: 2.4493. Min Act: -0.0000

Data Index: 1325120 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 3.3382. Min Range: -3.3382

Max Act: 2.3596. Min Act: -0.0000

Data Index: 1198813 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 3.3382. Min Range: -3.3382

Max Act: 2.0420. Min Act: -0.0000

Data Index: 1175048 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.9188. Min Act: -0.0000

Data Index: 1271077 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.9578. Min Act: -0.0000

Data Index: 1123904 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.8050. Min Act: -0.0000

Data Index: 528686 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.7907. Min Act: -0.0000

Data Index: 7271 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.7627. Min Act: -0.0000

Data Index: 1349312 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.6421. Min Act: -0.0000

Data Index: 232325 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.7164. Min Act: -0.0000

Data Index: 375329 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.6785. Min Act: -0.0000

Data Index: 1163528 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.6136. Min Act: -0.0000

Data Index: 549493 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.6141. Min Act: -0.0000

Data Index: 958793 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1176782 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.6860. Min Act: -0.0000

Data Index: 990700 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.5799. Min Act: -0.0000

Data Index: 790260 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.5717. Min Act: -0.0000

Data Index: 538946 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 3.3382. Min Range: -3.3382

Max Act: 1.5832. Min Act: -0.0000

Data Index: 403722 (C4 (Web Text))

Max Activating Token Index: 726