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

Dataset: The Pile

Neuron 1417 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: 1.3346. Min Range: -1.3346

Max Act: 1.3346. Min Act: -0.0000

Data Index: 1951399 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1228416 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1684932 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1046639 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1553571 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1787273 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1517714 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8870. Min Act: -0.0000

Data Index: 491845 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8544. Min Act: -0.0000

Data Index: 990113 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.7861. Min Act: -0.0000

Data Index: 919073 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8189. Min Act: -0.0000

Data Index: 123863 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8677. Min Act: -0.0000

Data Index: 689833 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1635389 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8341. Min Act: -0.0000

Data Index: 401876 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.7911. Min Act: -0.0000

Data Index: 555381 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1917804 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8635. Min Act: -0.0000

Data Index: 781622 (The Pile)

Max Activating Token Index: 623

Text #17

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.7614. Min Act: -0.0000

Data Index: 590477 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.8055. Min Act: -0.0000

Data Index: 426598 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 1.3346. Min Range: -1.3346

Max Act: 0.6553. Min Act: -0.0000

Data Index: 862355 (The Pile)

Max Activating Token Index: 698