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

Dataset: The Pile

Neuron 1341 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: 0.6749. Min Range: -0.6749

Max Act: 0.6730. Min Act: -0.0000

Data Index: 965842 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6749. Min Act: -0.0000

Data Index: 167552 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6608. Min Act: -0.0000

Data Index: 371576 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1745554 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5973. Min Act: -0.0000

Data Index: 901457 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1827343 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1610166 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1769721 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1709243 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5401. Min Act: -0.0000

Data Index: 321734 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1161761 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1394679 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4992. Min Act: -0.0000

Data Index: 231389 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1337514 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1914596 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1682925 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1566211 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4566. Min Act: 0.0000

Data Index: 1860816 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1801164 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4896. Min Act: -0.0000

Data Index: 608797 (The Pile)

Max Activating Token Index: 753