Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 192 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3293. Min Range: -4.3293

Max Act: 4.3293. Min Act: -0.0000

Data Index: 1614418 (Python Code)

Max Activating Token Index: 317

Text #1

Max Range: 4.3293. Min Range: -4.3293

Max Act: 4.1791. Min Act: -0.0000

Data Index: 1635441 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 4.3293. Min Range: -4.3293

Max Act: 4.1759. Min Act: -0.0000

Data Index: 1491545 (Python Code)

Max Activating Token Index: 864

Text #3

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.8766. Min Act: -0.0000

Data Index: 1529538 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.7800. Min Act: -0.0000

Data Index: 1510298 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.7705. Min Act: -0.0000

Data Index: 1383196 (Python Code)

Max Activating Token Index: 381

Text #6

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.5540. Min Act: -0.0000

Data Index: 1520385 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.5423. Min Act: -0.0000

Data Index: 1395703 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.7064. Min Act: -0.0000

Data Index: 1474691 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.4813. Min Act: -0.0000

Data Index: 1648085 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.3676. Min Act: -0.0000

Data Index: 1619309 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.3482. Min Act: -0.0000

Data Index: 1586852 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.2804. Min Act: -0.0000

Data Index: 1516166 (Python Code)

Max Activating Token Index: 661

Text #13

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.4046. Min Act: -0.0000

Data Index: 1620309 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.3271. Min Act: -0.0000

Data Index: 1629486 (Python Code)

Max Activating Token Index: 202

Text #15

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.3265. Min Act: -0.0000

Data Index: 1394722 (Python Code)

Max Activating Token Index: 383

Text #16

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.2986. Min Act: -0.0000

Data Index: 1494492 (Python Code)

Max Activating Token Index: 573

Text #17

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.4355. Min Act: -0.0000

Data Index: 1406420 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.2605. Min Act: -0.0000

Data Index: 1378702 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 4.3293. Min Range: -4.3293

Max Act: 3.0692. Min Act: -0.0000

Data Index: 1554905 (Python Code)

Max Activating Token Index: 926