Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4872 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.6021. Min Act: -0.0000

Data Index: 516343 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.8699. Min Act: -0.0000

Data Index: 1319870 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.9591. Min Act: -0.0000

Data Index: 563418 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.8820. Min Act: -0.0000

Data Index: 342381 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.4675. Min Act: -0.0000

Data Index: 1027422 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1096728 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.3963. Min Act: -0.0000

Data Index: 901664 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.2271. Min Act: -0.0000

Data Index: 211618 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.2021. Min Act: -0.0000

Data Index: 1275499 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.0225. Min Act: -0.0000

Data Index: 509674 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1353356 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.0554. Min Act: -0.0000

Data Index: 489582 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 1.9591. Min Range: -1.9591

Max Act: 1.0050. Min Act: 0.0001

Data Index: 465648 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.9591. Min Range: -1.9591

Max Act: 0.8694. Min Act: -0.0000

Data Index: 578932 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.9591. Min Range: -1.9591

Max Act: 0.8212. Min Act: -0.0000

Data Index: 449076 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.9591. Min Range: -1.9591

Max Act: 0.8682. Min Act: -0.0000

Data Index: 291839 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.9591. Min Range: -1.9591

Max Act: 0.8320. Min Act: 0.0001

Data Index: 990734 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 1.9591. Min Range: -1.9591

Max Act: 0.8017. Min Act: 0.0000

Data Index: 197558 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 1.9591. Min Range: -1.9591

Max Act: 0.8019. Min Act: 0.0001

Data Index: 12971 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.9591. Min Range: -1.9591

Max Act: 0.8086. Min Act: -0.0000

Data Index: 696518 (C4 (Web Text))

Max Activating Token Index: 392