Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3722 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1283819 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.8477. Min Act: -0.0000

Data Index: 311414 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1494132 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6601. Min Act: -0.0000

Data Index: 950711 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1327513 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1532506 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6692. Min Act: -0.0000

Data Index: 794802 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1215762 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6328. Min Act: -0.0000

Data Index: 74645 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1351023 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6382. Min Act: -0.0000

Data Index: 589396 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1131379 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1815766 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.4678. Min Act: -0.0000

Data Index: 396169 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1179705 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1172495 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1847919 (The Pile)

Max Activating Token Index: 912

Text #17

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.5290. Min Act: 0.0000

Data Index: 468187 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1368017 (The Pile)

Max Activating Token Index: 309

Text #19

Max Range: 0.9721. Min Range: -0.9721

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1460327 (The Pile)

Max Activating Token Index: 244