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

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

Neuron 1664 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.7622. Min Act: -0.0002

Data Index: 713758 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.7775. Min Act: -0.0002

Data Index: 1206789 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1040153 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6869. Min Act: -0.0002

Data Index: 254020 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6761. Min Act: -0.0001

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6272. Min Act: -0.0002

Data Index: 1097364 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6369. Min Act: -0.0001

Data Index: 1036135 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6548. Min Act: -0.0001

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6096. Min Act: -0.0002

Data Index: 475238 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6274. Min Act: -0.0001

Data Index: 140309 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.5959. Min Act: -0.0002

Data Index: 188772 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6626. Min Act: -0.0001

Data Index: 198950 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6587. Min Act: -0.0001

Data Index: 1207645 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6523. Min Act: -0.0002

Data Index: 131508 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6587. Min Act: -0.0002

Data Index: 1153166 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6005. Min Act: -0.0002

Data Index: 377015 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6359. Min Act: -0.0002

Data Index: 560309 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6790. Min Act: -0.0002

Data Index: 1314031 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6552. Min Act: -0.0001

Data Index: 696530 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.7775. Min Range: -0.7775

Max Act: 0.6287. Min Act: -0.0001

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 84