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

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

Neuron 3049 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1674. Min Act: -0.0001

Data Index: 188136 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1548. Min Act: -0.0001

Data Index: 2690 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1646. Min Act: -0.0002

Data Index: 1109929 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1565. Min Act: -0.0001

Data Index: 589913 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1554. Min Act: -0.0002

Data Index: 264491 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1411. Min Act: -0.0002

Data Index: 1000165 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1528. Min Act: -0.0002

Data Index: 1320672 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1590. Min Act: -0.0001

Data Index: 790701 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1624. Min Act: -0.0001

Data Index: 801530 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1156720 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1552. Min Act: -0.0002

Data Index: 461495 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1403. Min Act: -0.0002

Data Index: 435180 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1481. Min Act: -0.0002

Data Index: 1163873 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1611. Min Act: -0.0002

Data Index: 549170 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1592. Min Act: -0.0002

Data Index: 1321864 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1471. Min Act: -0.0001

Data Index: 921007 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1293007 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1535. Min Act: -0.0002

Data Index: 628495 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1573. Min Act: -0.0002

Data Index: 263484 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1562. Min Act: -0.0002

Data Index: 220725 (C4 (Web Text))

Max Activating Token Index: 766