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

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

Neuron 4608 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: 5.2684. Min Range: -5.2684

Max Act: 5.2684. Min Act: -0.0000

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.9963. Min Act: -0.0000

Data Index: 107445 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.9446. Min Act: -0.0000

Data Index: 999293 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.7580. Min Act: -0.0000

Data Index: 960348 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.7236. Min Act: -0.0000

Data Index: 1234031 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.5090. Min Act: -0.0000

Data Index: 1267930 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.6478. Min Act: -0.0000

Data Index: 1010565 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.8033. Min Act: -0.0000

Data Index: 1208508 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.5381. Min Act: -0.0000

Data Index: 720091 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.1702. Min Act: -0.0000

Data Index: 693542 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.3080. Min Act: -0.0000

Data Index: 185446 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.3020. Min Act: -0.0000

Data Index: 808950 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.2541. Min Act: -0.0000

Data Index: 331138 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.2439. Min Act: -0.0000

Data Index: 491587 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.2128. Min Act: -0.0000

Data Index: 328341 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.2286. Min Act: -0.0000

Data Index: 1181625 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.0488. Min Act: -0.0000

Data Index: 1240115 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.3726. Min Act: -0.0000

Data Index: 352090 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.1691. Min Act: -0.0000

Data Index: 1323331 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 5.2684. Min Range: -5.2684

Max Act: 4.0023. Min Act: -0.0000

Data Index: 609058 (C4 (Web Text))

Max Activating Token Index: 238