Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 952 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1780. Min Act: -0.0005

Data Index: 479207 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1795. Min Act: -0.0005

Data Index: 335215 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1586. Min Act: -0.0005

Data Index: 710442 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1722. Min Act: -0.0005

Data Index: 1281391 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1601. Min Act: -0.0005

Data Index: 629050 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1589. Min Act: -0.0005

Data Index: 1126271 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1543. Min Act: -0.0005

Data Index: 499127 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1486. Min Act: -0.0005

Data Index: 778857 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1481. Min Act: -0.0005

Data Index: 816223 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1470. Min Act: -0.0005

Data Index: 258217 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1475. Min Act: -0.0005

Data Index: 1297696 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1567. Min Act: -0.0005

Data Index: 888169 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1520. Min Act: -0.0005

Data Index: 813786 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1456. Min Act: -0.0005

Data Index: 1115149 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1454. Min Act: -0.0005

Data Index: 644812 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1417. Min Act: -0.0005

Data Index: 981638 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1406. Min Act: -0.0005

Data Index: 686275 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1445. Min Act: -0.0005

Data Index: 943481 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1451. Min Act: -0.0005

Data Index: 997316 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1392. Min Act: -0.0005

Data Index: 479495 (C4 (Web Text))

Max Activating Token Index: 404