Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2044 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0510. Min Act: -0.0006

Data Index: 841223 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0515. Min Act: -0.0006

Data Index: 1065478 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1274809 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0530. Min Act: -0.0006

Data Index: 567077 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0571. Min Act: -0.0006

Data Index: 984804 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0493. Min Act: -0.0006

Data Index: 1117894 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0457. Min Act: -0.0006

Data Index: 204877 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0520. Min Act: -0.0006

Data Index: 1291977 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1195063 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0469. Min Act: -0.0006

Data Index: 91200 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0489. Min Act: -0.0006

Data Index: 318959 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0428. Min Act: -0.0006

Data Index: 1028681 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0455. Min Act: -0.0006

Data Index: 474319 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1247278 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0479. Min Act: -0.0006

Data Index: 1045763 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0449. Min Act: -0.0005

Data Index: 341579 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0433. Min Act: -0.0006

Data Index: 818603 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0478. Min Act: -0.0006

Data Index: 928950 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0475. Min Act: -0.0006

Data Index: 937964 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0494. Min Act: -0.0006

Data Index: 419756 (C4 (Web Text))

Max Activating Token Index: 493