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

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

Neuron 2932 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0663. Min Act: -0.0001

Data Index: 893796 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0667. Min Act: -0.0001

Data Index: 974175 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0001

Data Index: 565501 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0597. Min Act: -0.0001

Data Index: 9355 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1086767 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1164800 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0560. Min Act: -0.0000

Data Index: 288895 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0551. Min Act: -0.0000

Data Index: 32467 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0549. Min Act: -0.0000

Data Index: 567863 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0494. Min Act: -0.0000

Data Index: 824271 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0467. Min Act: -0.0000

Data Index: 495729 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0520. Min Act: -0.0000

Data Index: 780019 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0500. Min Act: -0.0000

Data Index: 436679 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0573. Min Act: -0.0001

Data Index: 650747 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0512. Min Act: -0.0000

Data Index: 425881 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0527. Min Act: -0.0000

Data Index: 602054 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0525. Min Act: -0.0001

Data Index: 928714 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0541. Min Act: -0.0001

Data Index: 361489 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0542. Min Act: -0.0001

Data Index: 595529 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1013695 (C4 (Web Text))

Max Activating Token Index: 550