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

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

Neuron 307 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0001

Data Index: 794749 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1232681 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0497. Min Act: -0.0001

Data Index: 847850 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0488. Min Act: -0.0001

Data Index: 330709 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0491. Min Act: -0.0001

Data Index: 854971 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0405. Min Act: -0.0001

Data Index: 705077 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1265108 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0479. Min Act: -0.0001

Data Index: 963065 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0456. Min Act: -0.0001

Data Index: 69578 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1118010 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0431. Min Act: -0.0001

Data Index: 326769 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0465. Min Act: -0.0001

Data Index: 353129 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0390. Min Act: -0.0001

Data Index: 63672 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0413. Min Act: -0.0001

Data Index: 936358 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0481. Min Act: -0.0001

Data Index: 29681 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0394. Min Act: -0.0001

Data Index: 861656 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1498542 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0400. Min Act: -0.0001

Data Index: 726022 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1029569 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0383. Min Act: -0.0001

Data Index: 142158 (C4 (Web Text))

Max Activating Token Index: 100