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

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

Neuron 2544 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.6434. Min Act: -0.0001

Data Index: 254706 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1305171 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5997. Min Act: -0.0001

Data Index: 202980 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5689. Min Act: -0.0001

Data Index: 513770 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5588. Min Act: -0.0001

Data Index: 1567687 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1196353 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5851. Min Act: -0.0001

Data Index: 593813 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5696. Min Act: -0.0001

Data Index: 1346158 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5344. Min Act: -0.0001

Data Index: 1617442 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5496. Min Act: -0.0001

Data Index: 844650 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5092. Min Act: -0.0001

Data Index: 1489839 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5035. Min Act: -0.0001

Data Index: 373286 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4977. Min Act: -0.0001

Data Index: 1074887 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4975. Min Act: -0.0001

Data Index: 156379 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5064. Min Act: -0.0001

Data Index: 878224 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5248. Min Act: -0.0001

Data Index: 114553 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5183. Min Act: -0.0001

Data Index: 380895 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5220. Min Act: -0.0001

Data Index: 1147630 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4829. Min Act: -0.0001

Data Index: 384060 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5324. Min Act: -0.0001

Data Index: 1379713 (Python Code)

Max Activating Token Index: 747