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

Dataset: The Pile

Neuron 84 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: 1.2252. Min Range: -1.2252

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1259039 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0659. Min Act: -0.0000

Data Index: 759613 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8739. Min Act: -0.0000

Data Index: 483847 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8154. Min Act: -0.0000

Data Index: 368665 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8027. Min Act: -0.0000

Data Index: 822135 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7558. Min Act: -0.0000

Data Index: 581447 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8861. Min Act: -0.0000

Data Index: 455174 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7974. Min Act: -0.0000

Data Index: 889968 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1602738 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7900. Min Act: -0.0000

Data Index: 361114 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8407. Min Act: -0.0000

Data Index: 309199 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1636000 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8021. Min Act: -0.0000

Data Index: 799247 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7911. Min Act: -0.0000

Data Index: 595247 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1984884 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1701386 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8103. Min Act: -0.0000

Data Index: 519818 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1898617 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1940104 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7438. Min Act: -0.0000

Data Index: 58436 (The Pile)

Max Activating Token Index: 679