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

Dataset: The Pile

Neuron 1308 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: 0.9102. Min Range: -0.9102

Max Act: 0.9102. Min Act: -0.0000

Data Index: 1860959 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1465498 (The Pile)

Max Activating Token Index: 332

Text #2

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1545158 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7661. Min Act: -0.0000

Data Index: 814989 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1317402 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7544. Min Act: -0.0001

Data Index: 729811 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1211625 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7478. Min Act: -0.0000

Data Index: 733555 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1348781 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1282214 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1754365 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7565. Min Act: -0.0000

Data Index: 833680 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1657771 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1807068 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7565. Min Act: -0.0000

Data Index: 308569 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1384752 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1924137 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1700152 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1176200 (The Pile)

Max Activating Token Index: 7

Text #19

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1389680 (The Pile)

Max Activating Token Index: 634