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

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

Neuron 3346 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: 0.8405. Min Range: -0.8405

Max Act: 0.8212. Min Act: -0.0001

Data Index: 901377 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.8405. Min Act: -0.0001

Data Index: 436748 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7716. Min Act: -0.0001

Data Index: 89394 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7403. Min Act: -0.0001

Data Index: 1166387 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7672. Min Act: -0.0001

Data Index: 775238 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7394. Min Act: -0.0001

Data Index: 1358758 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7584. Min Act: -0.0001

Data Index: 1281106 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7570. Min Act: -0.0001

Data Index: 1160493 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7726. Min Act: -0.0001

Data Index: 724055 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7429. Min Act: -0.0001

Data Index: 1231864 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6817. Min Act: -0.0001

Data Index: 87518 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6924. Min Act: -0.0001

Data Index: 885001 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.7840. Min Act: -0.0001

Data Index: 320380 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6617. Min Act: -0.0001

Data Index: 630809 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6822. Min Act: -0.0001

Data Index: 1208472 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6756. Min Act: -0.0001

Data Index: 18436 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6987. Min Act: -0.0001

Data Index: 1163049 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6892. Min Act: -0.0001

Data Index: 403306 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6699. Min Act: -0.0001

Data Index: 711776 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.8405. Min Range: -0.8405

Max Act: 0.6537. Min Act: -0.0001

Data Index: 540922 (C4 (Web Text))

Max Activating Token Index: 238