Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 799 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8278. Min Act: -0.0001

Data Index: 137045 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8706. Min Act: -0.0001

Data Index: 356485 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8582. Min Act: -0.0001

Data Index: 670422 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8384. Min Act: -0.0001

Data Index: 294983 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8168. Min Act: -0.0001

Data Index: 214730 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8410. Min Act: -0.0001

Data Index: 757309 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7520. Min Act: -0.0001

Data Index: 400381 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8259. Min Act: -0.0001

Data Index: 846707 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7864. Min Act: -0.0001

Data Index: 654292 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7599. Min Act: -0.0001

Data Index: 418435 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8151. Min Act: -0.0001

Data Index: 1037864 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7551. Min Act: -0.0001

Data Index: 241137 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8104. Min Act: -0.0001

Data Index: 375493 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7726. Min Act: -0.0001

Data Index: 72917 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7702. Min Act: -0.0001

Data Index: 84776 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7497. Min Act: -0.0001

Data Index: 190039 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7445. Min Act: -0.0001

Data Index: 815994 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7708. Min Act: -0.0001

Data Index: 488863 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7937. Min Act: -0.0001

Data Index: 63479 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7427. Min Act: -0.0001

Data Index: 796186 (C4 (Web Text))

Max Activating Token Index: 969