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

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

Neuron 750 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1393833 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6230. Min Act: -0.0000

Data Index: 759040 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1504756 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1645248 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1523631 (Python Code)

Max Activating Token Index: 427

Text #5

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1638979 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1567325 (Python Code)

Max Activating Token Index: 637

Text #7

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1418695 (Python Code)

Max Activating Token Index: 542

Text #8

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5314. Min Act: -0.0000

Data Index: 422409 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1262578 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4932. Min Act: -0.0000

Data Index: 643276 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4801. Min Act: -0.0000

Data Index: 644691 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4986. Min Act: -0.0000

Data Index: 492543 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1601066 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4744. Min Act: -0.0000

Data Index: 780837 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1616443 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1046822 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4650. Min Act: -0.0000

Data Index: 716993 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1554753 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4457. Min Act: -0.0000

Data Index: 112373 (C4 (Web Text))

Max Activating Token Index: 380