Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2561 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1472736 (Python Code)

Max Activating Token Index: 501

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0001

Data Index: 638861 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0567. Min Act: -0.0001

Data Index: 183173 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1508132 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0554. Min Act: -0.0001

Data Index: 457204 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1313587 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1437093 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0527. Min Act: -0.0001

Data Index: 174769 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0519. Min Act: -0.0001

Data Index: 324703 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1341867 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1117531 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1256375 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0489. Min Act: -0.0001

Data Index: 499606 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0487. Min Act: -0.0001

Data Index: 849284 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0481. Min Act: -0.0001

Data Index: 334356 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0484. Min Act: -0.0001

Data Index: 718368 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0479. Min Act: -0.0001

Data Index: 901405 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1330676 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1312326 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1257097 (C4 (Web Text))

Max Activating Token Index: 319