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

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

Neuron 3689 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.5528. Min Act: 0.0000

Data Index: 715923 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1118616 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4579. Min Act: -0.0000

Data Index: 754314 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4438. Min Act: -0.0000

Data Index: 884551 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4207. Min Act: -0.0000

Data Index: 663957 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1344041 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3986. Min Act: -0.0000

Data Index: 220700 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3834. Min Act: -0.0000

Data Index: 256826 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3549. Min Act: -0.0000

Data Index: 504205 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3698. Min Act: -0.0000

Data Index: 597409 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1173168 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3421. Min Act: -0.0000

Data Index: 582584 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3405. Min Act: -0.0000

Data Index: 672919 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1108879 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3366. Min Act: -0.0000

Data Index: 380903 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1157875 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1307615 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3384. Min Act: -0.0000

Data Index: 384116 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1311261 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3308. Min Act: -0.0000

Data Index: 694310 (C4 (Web Text))

Max Activating Token Index: 783