Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3333 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0002

Data Index: 712695 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1733. Min Act: -0.0002

Data Index: 460422 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1667. Min Act: -0.0002

Data Index: 1239990 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1648. Min Act: -0.0002

Data Index: 508382 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1592. Min Act: -0.0002

Data Index: 515121 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1593. Min Act: -0.0002

Data Index: 275973 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1542. Min Act: -0.0002

Data Index: 345585 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1558. Min Act: -0.0002

Data Index: 94276 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1543. Min Act: -0.0002

Data Index: 227866 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1562. Min Act: -0.0002

Data Index: 509795 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1529. Min Act: -0.0002

Data Index: 202729 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1513. Min Act: -0.0002

Data Index: 843969 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1542. Min Act: -0.0002

Data Index: 430040 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1525. Min Act: -0.0002

Data Index: 1117251 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1514. Min Act: -0.0002

Data Index: 459920 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1527. Min Act: -0.0002

Data Index: 582720 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1489. Min Act: -0.0002

Data Index: 490909 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1507. Min Act: -0.0002

Data Index: 512022 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1494. Min Act: -0.0002

Data Index: 1073888 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1514. Min Act: -0.0002

Data Index: 395592 (C4 (Web Text))

Max Activating Token Index: 341