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

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

Neuron 2611 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1607. Min Range: -2.1607

Max Act: 2.1607. Min Act: -0.0001

Data Index: 751691 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 2.1607. Min Range: -2.1607

Max Act: 2.0918. Min Act: -0.0000

Data Index: 1288174 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.9357. Min Act: -0.0000

Data Index: 475956 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.7639. Min Act: -0.0000

Data Index: 803337 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.9752. Min Act: -0.0000

Data Index: 589717 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8721. Min Act: -0.0000

Data Index: 301854 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.9431. Min Act: -0.0000

Data Index: 1297235 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8469. Min Act: -0.0000

Data Index: 147667 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.6475. Min Act: -0.0000

Data Index: 55164 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.7485. Min Act: -0.0001

Data Index: 688557 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.6196. Min Act: -0.0001

Data Index: 173244 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.6975. Min Act: -0.0001

Data Index: 518733 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.4975. Min Act: -0.0001

Data Index: 1242541 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.4829. Min Act: -0.0001

Data Index: 414485 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.6433. Min Act: -0.0000

Data Index: 300731 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.6430. Min Act: -0.0001

Data Index: 303748 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.5952. Min Act: -0.0001

Data Index: 261336 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1070048 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.6940. Min Act: -0.0001

Data Index: 1269790 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1170127 (C4 (Web Text))

Max Activating Token Index: 5