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

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

Neuron 5070 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0000

Data Index: 137122 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0666. Min Act: -0.0000

Data Index: 624821 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1562494 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1045439 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0620. Min Act: -0.0000

Data Index: 662188 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0658. Min Act: 0.0000

Data Index: 1554506 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0553. Min Act: -0.0000

Data Index: 335196 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1219358 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0563. Min Act: -0.0000

Data Index: 1648032 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0484. Min Act: -0.0000

Data Index: 115957 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1444411 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0509. Min Act: -0.0000

Data Index: 763731 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0533. Min Act: -0.0000

Data Index: 152628 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0477. Min Act: -0.0000

Data Index: 190174 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0481. Min Act: -0.0000

Data Index: 970326 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1088102 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0464. Min Act: -0.0000

Data Index: 365104 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1399551 (Python Code)

Max Activating Token Index: 483

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1597715 (Python Code)

Max Activating Token Index: 745

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1052905 (C4 (Web Text))

Max Activating Token Index: 541