Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1468 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1542. Min Act: -0.0002

Data Index: 384260 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1536. Min Act: -0.0002

Data Index: 600662 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1526. Min Act: -0.0002

Data Index: 191782 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1466. Min Act: -0.0002

Data Index: 134627 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1579. Min Act: -0.0002

Data Index: 663800 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1507. Min Act: -0.0002

Data Index: 892533 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1608. Min Act: -0.0002

Data Index: 368039 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1498. Min Act: -0.0002

Data Index: 1209836 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1410. Min Act: -0.0002

Data Index: 48584 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1403. Min Act: -0.0002

Data Index: 21034 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1456. Min Act: -0.0002

Data Index: 1226189 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1491. Min Act: -0.0002

Data Index: 871070 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1445. Min Act: -0.0002

Data Index: 444695 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1502. Min Act: -0.0002

Data Index: 367115 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1439. Min Act: -0.0002

Data Index: 1114627 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1597. Min Act: -0.0002

Data Index: 634271 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1488. Min Act: -0.0002

Data Index: 213001 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1497. Min Act: -0.0002

Data Index: 407293 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1530. Min Act: -0.0002

Data Index: 950225 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1435. Min Act: -0.0002

Data Index: 922199 (C4 (Web Text))

Max Activating Token Index: 685