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

Dataset: The Pile

Neuron 2652 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5189. Min Range: -3.5189

Max Act: 3.5189. Min Act: 0.0001

Data Index: 1569181 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.8278. Min Act: -0.0000

Data Index: 1995221 (The Pile)

Max Activating Token Index: 536

Text #2

Max Range: 3.5189. Min Range: -3.5189

Max Act: 3.2055. Min Act: -0.0000

Data Index: 230442 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 3.5189. Min Range: -3.5189

Max Act: 3.2611. Min Act: -0.0000

Data Index: 708341 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.8084. Min Act: -0.0000

Data Index: 1250520 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.2555. Min Act: -0.0000

Data Index: 350794 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.8092. Min Act: -0.0000

Data Index: 1825104 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.5158. Min Act: -0.0000

Data Index: 586376 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.5258. Min Act: -0.0000

Data Index: 1917424 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.2698. Min Act: -0.0000

Data Index: 141201 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.2312. Min Act: -0.0000

Data Index: 1142070 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 3.5189. Min Range: -3.5189

Max Act: 2.2540. Min Act: -0.0000

Data Index: 957246 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 3.5189. Min Range: -3.5189

Max Act: 1.9910. Min Act: -0.0000

Data Index: 1448366 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 3.5189. Min Range: -3.5189

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1473474 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 3.5189. Min Range: -3.5189

Max Act: 1.9489. Min Act: -0.0000

Data Index: 64156 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 3.5189. Min Range: -3.5189

Max Act: 1.8415. Min Act: -0.0000

Data Index: 879472 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 3.5189. Min Range: -3.5189

Max Act: 1.6922. Min Act: -0.0000

Data Index: 1936118 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 3.5189. Min Range: -3.5189

Max Act: 1.7462. Min Act: -0.0000

Data Index: 938203 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 3.5189. Min Range: -3.5189

Max Act: 1.8242. Min Act: -0.0000

Data Index: 1898673 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 3.5189. Min Range: -3.5189

Max Act: 1.6819. Min Act: -0.0000

Data Index: 1322643 (The Pile)

Max Activating Token Index: 430