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

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

Neuron 1306 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: 1.0738. Min Range: -1.0738

Max Act: 1.0738. Min Act: -0.0001

Data Index: 17377 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.0738. Min Range: -1.0738

Max Act: 1.0422. Min Act: -0.0001

Data Index: 963433 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.9551. Min Act: -0.0001

Data Index: 767250 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.9614. Min Act: -0.0001

Data Index: 250449 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.8925. Min Act: -0.0001

Data Index: 617945 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.8259. Min Act: -0.0001

Data Index: 471107 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.9006. Min Act: -0.0001

Data Index: 782305 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.8595. Min Act: -0.0001

Data Index: 317841 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1225774 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7812. Min Act: -0.0001

Data Index: 162932 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7789. Min Act: -0.0001

Data Index: 1132150 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7856. Min Act: -0.0001

Data Index: 1074841 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7666. Min Act: -0.0001

Data Index: 977486 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7659. Min Act: -0.0001

Data Index: 930266 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7874. Min Act: -0.0001

Data Index: 527847 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7382. Min Act: -0.0001

Data Index: 642244 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7905. Min Act: -0.0001

Data Index: 1319538 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7667. Min Act: -0.0001

Data Index: 983463 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7625. Min Act: -0.0001

Data Index: 143835 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7608. Min Act: -0.0001

Data Index: 1205042 (C4 (Web Text))

Max Activating Token Index: 926