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

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

Neuron 5706 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8506. Min Range: -5.8506

Max Act: 5.8506. Min Act: -0.0000

Data Index: 620645 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.9681. Min Act: -0.0000

Data Index: 1236894 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 5.8506. Min Range: -5.8506

Max Act: 5.1173. Min Act: -0.0000

Data Index: 1022963 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 5.8506. Min Range: -5.8506

Max Act: 5.1365. Min Act: -0.0000

Data Index: 859215 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.9260. Min Act: -0.0000

Data Index: 1174762 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.8984. Min Act: -0.0000

Data Index: 708660 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.6664. Min Act: -0.0001

Data Index: 311414 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.4466. Min Act: -0.0000

Data Index: 435533 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.7974. Min Act: -0.0000

Data Index: 1068278 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.8060. Min Act: -0.0001

Data Index: 559875 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.9393. Min Act: -0.0001

Data Index: 1178113 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.7716. Min Act: -0.0000

Data Index: 838560 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.4137. Min Act: -0.0001

Data Index: 1258712 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.7274. Min Act: -0.0000

Data Index: 319511 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.1852. Min Act: -0.0000

Data Index: 720043 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.3731. Min Act: -0.0000

Data Index: 246797 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.3342. Min Act: -0.0000

Data Index: 412062 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.8008. Min Act: -0.0000

Data Index: 308759 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.2792. Min Act: -0.0000

Data Index: 1378042 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 5.8506. Min Range: -5.8506

Max Act: 4.4012. Min Act: -0.0000

Data Index: 1619219 (Python Code)

Max Activating Token Index: 105