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

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

Neuron 3811 in Layer 0

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: 0.2733. Min Range: -0.2733

Max Act: 0.2733. Min Act: -0.0001

Data Index: 1462464 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2699. Min Act: -0.0001

Data Index: 1547168 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1650142 (Python Code)

Max Activating Token Index: 127

Text #3

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2592. Min Act: -0.0001

Data Index: 1453318 (Python Code)

Max Activating Token Index: 336

Text #4

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2599. Min Act: -0.0001

Data Index: 1390200 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2648. Min Act: -0.0001

Data Index: 1468683 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1467900 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2597. Min Act: -0.0001

Data Index: 1526048 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1550382 (Python Code)

Max Activating Token Index: 498

Text #9

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1368573 (Python Code)

Max Activating Token Index: 767

Text #10

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2547. Min Act: -0.0001

Data Index: 1375406 (Python Code)

Max Activating Token Index: 443

Text #11

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2598. Min Act: -0.0001

Data Index: 1394293 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2597. Min Act: -0.0001

Data Index: 1649862 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1500614 (Python Code)

Max Activating Token Index: 738

Text #14

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1642716 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2572. Min Act: -0.0001

Data Index: 1393755 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1382407 (Python Code)

Max Activating Token Index: 805

Text #17

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1556679 (Python Code)

Max Activating Token Index: 602

Text #18

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1637409 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1513963 (Python Code)

Max Activating Token Index: 536