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

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

Neuron 2783 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.9338. Min Act: -0.0001

Data Index: 659981 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.0571. Min Range: -1.0571

Max Act: 1.0491. Min Act: -0.0001

Data Index: 728755 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.0571. Min Range: -1.0571

Max Act: 1.0425. Min Act: -0.0001

Data Index: 884419 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 1.0571. Min Range: -1.0571

Max Act: 1.0571. Min Act: -0.0001

Data Index: 1133561 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.0571. Min Range: -1.0571

Max Act: 1.0320. Min Act: -0.0001

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.9732. Min Act: -0.0001

Data Index: 1184876 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 1.0571. Min Range: -1.0571

Max Act: 1.0089. Min Act: -0.0001

Data Index: 1167962 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.8778. Min Act: -0.0001

Data Index: 801481 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 1.0571. Min Range: -1.0571

Max Act: 1.0371. Min Act: -0.0001

Data Index: 900318 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.9593. Min Act: -0.0001

Data Index: 1043173 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.8817. Min Act: -0.0001

Data Index: 1064781 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.8613. Min Act: -0.0001

Data Index: 68551 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.9001. Min Act: -0.0001

Data Index: 841656 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.9244. Min Act: -0.0001

Data Index: 104025 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.6949. Min Act: -0.0001

Data Index: 555129 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.8881. Min Act: -0.0001

Data Index: 492965 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.7845. Min Act: -0.0001

Data Index: 399636 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.9650. Min Act: -0.0001

Data Index: 1008685 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.8839. Min Act: -0.0001

Data Index: 120296 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 1.0571. Min Range: -1.0571

Max Act: 0.8764. Min Act: -0.0001

Data Index: 914417 (C4 (Web Text))

Max Activating Token Index: 894