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

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

Neuron 4793 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4549. Min Act: -0.0001

Data Index: 620817 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4017. Min Act: -0.0001

Data Index: 656138 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3760. Min Act: -0.0001

Data Index: 694229 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4175. Min Act: -0.0001

Data Index: 754044 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3873. Min Act: -0.0001

Data Index: 149950 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3920. Min Act: -0.0001

Data Index: 588591 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3880. Min Act: -0.0001

Data Index: 967896 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3614. Min Act: -0.0001

Data Index: 708963 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3734. Min Act: -0.0001

Data Index: 449787 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3821. Min Act: -0.0001

Data Index: 988839 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3818. Min Act: -0.0001

Data Index: 817787 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3620. Min Act: -0.0001

Data Index: 213609 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3633. Min Act: -0.0001

Data Index: 1172891 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3708. Min Act: -0.0001

Data Index: 419579 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3880. Min Act: -0.0001

Data Index: 280474 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1066509 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3853. Min Act: -0.0001

Data Index: 82568 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3580. Min Act: -0.0001

Data Index: 816571 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3702. Min Act: -0.0001

Data Index: 489970 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3737. Min Act: -0.0001

Data Index: 803194 (C4 (Web Text))

Max Activating Token Index: 263