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

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

Neuron 1512 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.2325. Min Act: -0.0000

Data Index: 119469 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0671. Min Act: -0.0000

Data Index: 151698 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1292288 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1108702 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9403. Min Act: -0.0000

Data Index: 844176 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1097947 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1127253 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9017. Min Act: -0.0000

Data Index: 252671 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1101648 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1315742 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8502. Min Act: -0.0000

Data Index: 912856 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1045731 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1209333 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1242610 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1174747 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8370. Min Act: -0.0000

Data Index: 534742 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8045. Min Act: -0.0000

Data Index: 127648 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1046334 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.7720. Min Act: -0.0000

Data Index: 39012 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.7670. Min Act: -0.0000

Data Index: 996771 (C4 (Web Text))

Max Activating Token Index: 24