Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4915 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.5105. Min Act: -0.0000

Data Index: 648643 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4384. Min Act: -0.0000

Data Index: 120726 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1339433 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.4117. Min Act: -0.0000

Data Index: 779645 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3645. Min Act: -0.0000

Data Index: 8559 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3858. Min Act: -0.0000

Data Index: 956627 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3673. Min Act: -0.0000

Data Index: 43127 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3524. Min Act: -0.0000

Data Index: 237269 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3424. Min Act: -0.0000

Data Index: 909747 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1015293 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1157317 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3372. Min Act: -0.0000

Data Index: 54493 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3413. Min Act: -0.0000

Data Index: 855857 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3317. Min Act: -0.0000

Data Index: 431389 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3071. Min Act: -0.0000

Data Index: 243775 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3084. Min Act: -0.0000

Data Index: 639032 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3222. Min Act: -0.0000

Data Index: 790942 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3321. Min Act: -0.0000

Data Index: 775789 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3190. Min Act: -0.0000

Data Index: 398607 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.5105. Min Range: -0.5105

Max Act: 0.3472. Min Act: -0.0000

Data Index: 273620 (C4 (Web Text))

Max Activating Token Index: 952