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

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

Neuron 2409 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: 2.2677. Min Range: -2.2677

Max Act: 2.2677. Min Act: -0.0000

Data Index: 1099436 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 2.2677. Min Range: -2.2677

Max Act: 2.1546. Min Act: -0.0000

Data Index: 934881 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.9560. Min Act: -0.0000

Data Index: 735895 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.8171. Min Act: -0.0000

Data Index: 155231 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.7025. Min Act: -0.0000

Data Index: 872209 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.5848. Min Act: -0.0000

Data Index: 56932 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.5819. Min Act: -0.0000

Data Index: 1171412 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.6029. Min Act: -0.0000

Data Index: 223895 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.4870. Min Act: -0.0000

Data Index: 170492 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.6465. Min Act: -0.0000

Data Index: 464732 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.5575. Min Act: -0.0000

Data Index: 205720 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.4556. Min Act: -0.0000

Data Index: 960755 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.6524. Min Act: -0.0000

Data Index: 962092 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.5077. Min Act: -0.0000

Data Index: 519160 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.4876. Min Act: -0.0000

Data Index: 1324220 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.4635. Min Act: -0.0000

Data Index: 144882 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1143754 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.4563. Min Act: -0.0000

Data Index: 1234005 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1339657 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 2.2677. Min Range: -2.2677

Max Act: 1.4324. Min Act: -0.0000

Data Index: 1247195 (C4 (Web Text))

Max Activating Token Index: 380