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

Dataset: The Pile

Neuron 2537 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.4279. Min Act: -0.0000

Data Index: 149202 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3579. Min Act: -0.0000

Data Index: 952836 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2906. Min Act: -0.0000

Data Index: 567000 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1770031 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3017. Min Act: -0.0000

Data Index: 564080 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2628. Min Act: -0.0000

Data Index: 526531 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1146520 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1710783 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.3050. Min Act: -0.0000

Data Index: 810877 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2771. Min Act: -0.0000

Data Index: 201451 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2843. Min Act: -0.0000

Data Index: 48944 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1566048 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2810. Min Act: -0.0000

Data Index: 124980 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2768. Min Act: -0.0000

Data Index: 29780 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1596573 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1236365 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1376254 (The Pile)

Max Activating Token Index: 165

Text #17

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1301249 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1789836 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 0.4279. Min Range: -0.4279

Max Act: 0.2339. Min Act: -0.0000

Data Index: 681810 (The Pile)

Max Activating Token Index: 505