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

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

Neuron 1065 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1232300 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1471011 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1520789 (Python Code)

Max Activating Token Index: 984

Text #3

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1536335 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1465190 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1392066 (Python Code)

Max Activating Token Index: 362

Text #6

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1613304 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1638937 (Python Code)

Max Activating Token Index: 459

Text #8

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1587682 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2608. Min Act: -0.0001

Data Index: 1458568 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2591. Min Act: -0.0001

Data Index: 1459280 (Python Code)

Max Activating Token Index: 978

Text #11

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1548407 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2523. Min Act: -0.0001

Data Index: 1543495 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2498. Min Act: -0.0001

Data Index: 1532083 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1536090 (Python Code)

Max Activating Token Index: 271

Text #15

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2374. Min Act: -0.0001

Data Index: 1616864 (Python Code)

Max Activating Token Index: 558

Text #16

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1536393 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2337. Min Act: -0.0001

Data Index: 1497678 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1535551 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2406. Min Act: -0.0001

Data Index: 1484268 (Python Code)

Max Activating Token Index: 366