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

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

Neuron 119 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2613. Min Act: -0.0001

Data Index: 552345 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2110. Min Act: -0.0001

Data Index: 506743 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2085. Min Act: -0.0001

Data Index: 290201 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1789. Min Act: -0.0001

Data Index: 579025 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1879. Min Act: -0.0001

Data Index: 495961 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1353735 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1569. Min Act: -0.0001

Data Index: 385846 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1042491 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1674. Min Act: -0.0001

Data Index: 580486 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1528. Min Act: -0.0001

Data Index: 733547 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1634. Min Act: -0.0001

Data Index: 741725 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1517. Min Act: -0.0001

Data Index: 766172 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1510. Min Act: -0.0001

Data Index: 772534 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1693. Min Act: -0.0001

Data Index: 345315 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1627. Min Act: -0.0001

Data Index: 900293 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1393. Min Act: -0.0001

Data Index: 291293 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1592. Min Act: -0.0001

Data Index: 452300 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1492. Min Act: -0.0001

Data Index: 126116 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1091168 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1144408 (C4 (Web Text))

Max Activating Token Index: 862