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

Dataset: The Pile

Neuron 4568 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8558. Min Act: -0.0000

Data Index: 1619893 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.5051. Min Act: -0.0000

Data Index: 696717 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3302. Min Act: -0.0000

Data Index: 1254389 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.5236. Min Act: -0.0000

Data Index: 171429 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1839884 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4356. Min Act: -0.0000

Data Index: 621736 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1870071 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3821. Min Act: -0.0000

Data Index: 228675 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3901. Min Act: -0.0000

Data Index: 335534 (The Pile)

Max Activating Token Index: 720

Text #9

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3630. Min Act: -0.0000

Data Index: 1929332 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3330. Min Act: -0.0000

Data Index: 591678 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1807772 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3192. Min Act: -0.0000

Data Index: 58187 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4288. Min Act: -0.0000

Data Index: 1469838 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1453003 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.2711. Min Act: -0.0000

Data Index: 701288 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.2698. Min Act: -0.0000

Data Index: 1959629 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1821686 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.2096. Min Act: -0.0000

Data Index: 897155 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.0700. Min Act: -0.0000

Data Index: 146497 (The Pile)

Max Activating Token Index: 783