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

Dataset: The Pile

Neuron 129 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.3070. Min Act: -0.0000

Data Index: 836463 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2850. Min Act: -0.0000

Data Index: 710024 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1407456 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1903192 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1368199 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.3031. Min Act: -0.0000

Data Index: 506480 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1573600 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2723. Min Act: -0.0000

Data Index: 871982 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1243915 (The Pile)

Max Activating Token Index: 391

Text #9

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1109251 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2436. Min Act: -0.0000

Data Index: 38971 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1422876 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2359. Min Act: -0.0000

Data Index: 436219 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1951604 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2092. Min Act: -0.0000

Data Index: 496657 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1605351 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1221995 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1679001 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1550536 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 0.3070. Min Range: -0.3070

Max Act: 0.2641. Min Act: -0.0000

Data Index: 422987 (The Pile)

Max Activating Token Index: 877