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

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

Neuron 350 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1528. Min Range: -2.1528

Max Act: 2.1528. Min Act: -0.0000

Data Index: 91254 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.9039. Min Act: -0.0000

Data Index: 1235328 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.9803. Min Act: -0.0000

Data Index: 1339005 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 2.1528. Min Range: -2.1528

Max Act: 2.0068. Min Act: -0.0000

Data Index: 311681 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 2.1528. Min Range: -2.1528

Max Act: 2.1295. Min Act: -0.0000

Data Index: 156726 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.8167. Min Act: -0.0000

Data Index: 341573 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.6811. Min Act: -0.0000

Data Index: 269662 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.8713. Min Act: -0.0000

Data Index: 1206723 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.7187. Min Act: -0.0000

Data Index: 1151717 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.7659. Min Act: -0.0000

Data Index: 979786 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.6857. Min Act: -0.0000

Data Index: 123086 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.7649. Min Act: -0.0000

Data Index: 1265056 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.6059. Min Act: -0.0000

Data Index: 1307312 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.6464. Min Act: -0.0000

Data Index: 158475 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.6018. Min Act: -0.0000

Data Index: 523335 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.7353. Min Act: -0.0000

Data Index: 530449 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.6759. Min Act: -0.0000

Data Index: 761611 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.6731. Min Act: -0.0000

Data Index: 197050 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.4909. Min Act: -0.0000

Data Index: 511024 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 2.1528. Min Range: -2.1528

Max Act: 1.6857. Min Act: -0.0000

Data Index: 77845 (C4 (Web Text))

Max Activating Token Index: 882