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

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

Neuron 1470 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: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0002

Data Index: 646010 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0654. Min Act: -0.0002

Data Index: 458108 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0638. Min Act: -0.0002

Data Index: 410022 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1276811 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1542585 (Python Code)

Max Activating Token Index: 439

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1215758 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1653261 (Python Code)

Max Activating Token Index: 604

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1421955 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1533261 (Python Code)

Max Activating Token Index: 538

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0595. Min Act: -0.0002

Data Index: 970656 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1408307 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1435416 (Python Code)

Max Activating Token Index: 507

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0576. Min Act: -0.0002

Data Index: 207449 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1536151 (Python Code)

Max Activating Token Index: 315

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1469724 (Python Code)

Max Activating Token Index: 956

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1636612 (Python Code)

Max Activating Token Index: 284

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1596859 (Python Code)

Max Activating Token Index: 842

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1645533 (Python Code)

Max Activating Token Index: 720

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1489073 (Python Code)

Max Activating Token Index: 803

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1533590 (Python Code)

Max Activating Token Index: 652