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

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

Neuron 3351 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: 1.3895. Min Range: -1.3895

Max Act: 1.3559. Min Act: -0.0001

Data Index: 999768 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2866. Min Act: -0.0001

Data Index: 137984 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.3895. Min Act: -0.0000

Data Index: 868408 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2324. Min Act: -0.0001

Data Index: 792323 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1090. Min Act: -0.0001

Data Index: 192860 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0698. Min Act: -0.0001

Data Index: 1109317 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0940. Min Act: -0.0001

Data Index: 215676 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0465. Min Act: -0.0001

Data Index: 944989 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1109. Min Act: -0.0001

Data Index: 33821 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0395. Min Act: -0.0001

Data Index: 133559 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0660. Min Act: -0.0001

Data Index: 745127 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0830. Min Act: -0.0001

Data Index: 334256 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0474. Min Act: -0.0000

Data Index: 657328 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.3895. Min Range: -1.3895

Max Act: 0.9909. Min Act: -0.0001

Data Index: 269880 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0172. Min Act: -0.0001

Data Index: 205348 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0351. Min Act: -0.0001

Data Index: 331227 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0656. Min Act: -0.0001

Data Index: 1285479 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1003. Min Act: -0.0001

Data Index: 538196 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0009. Min Act: -0.0001

Data Index: 131628 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0667. Min Act: -0.0001

Data Index: 21126 (C4 (Web Text))

Max Activating Token Index: 750