Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2590 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0683. Min Act: -0.0000

Data Index: 889193 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0687. Min Act: -0.0000

Data Index: 41438 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1204811 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1406584 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1104442 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0635. Min Act: -0.0000

Data Index: 631387 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0649. Min Act: -0.0000

Data Index: 188276 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1052931 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1520085 (Python Code)

Max Activating Token Index: 814

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1432858 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0599. Min Act: -0.0000

Data Index: 888191 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1593234 (Python Code)

Max Activating Token Index: 929

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0576. Min Act: -0.0000

Data Index: 706752 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1496794 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1488402 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1136155 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1633990 (Python Code)

Max Activating Token Index: 613

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1415258 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1487511 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1381633 (Python Code)

Max Activating Token Index: 752