Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3049 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.4615. Min Act: -0.0000

Data Index: 825956 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1102762 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3491. Min Act: -0.0000

Data Index: 342173 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3706. Min Act: -0.0000

Data Index: 739111 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3699. Min Act: -0.0000

Data Index: 861733 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3714. Min Act: -0.0001

Data Index: 462542 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3575. Min Act: -0.0000

Data Index: 884985 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3512. Min Act: -0.0000

Data Index: 54309 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3338. Min Act: -0.0001

Data Index: 504877 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3392. Min Act: -0.0000

Data Index: 758397 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3328. Min Act: -0.0001

Data Index: 852544 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1073986 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.2925. Min Act: -0.0001

Data Index: 976392 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3439. Min Act: -0.0000

Data Index: 61578 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.3128. Min Act: -0.0000

Data Index: 399921 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.2864. Min Act: -0.0001

Data Index: 370486 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.2817. Min Act: -0.0001

Data Index: 54293 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.2822. Min Act: -0.0001

Data Index: 1287857 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.2801. Min Act: -0.0000

Data Index: 368839 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.4615. Min Range: -0.4615

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1079123 (C4 (Web Text))

Max Activating Token Index: 720