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

Dataset: The Pile

Neuron 4197 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1641. Min Act: -0.0000

Data Index: 732025 (The Pile)

Max Activating Token Index: 507

Text #1

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1668047 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1493406 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.9510. Min Act: -0.0000

Data Index: 555621 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.9229. Min Act: -0.0000

Data Index: 319520 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1970259 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1805520 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1698957 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1985986 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8875. Min Act: -0.0000

Data Index: 833254 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8898. Min Act: -0.0000

Data Index: 494327 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8889. Min Act: -0.0000

Data Index: 138255 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8405. Min Act: -0.0000

Data Index: 815855 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1893583 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8359. Min Act: -0.0000

Data Index: 387909 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8582. Min Act: -0.0000

Data Index: 613172 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8978. Min Act: -0.0000

Data Index: 666876 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1685796 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8436. Min Act: -0.0000

Data Index: 874267 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 1.1641. Min Range: -1.1641

Max Act: 0.8221. Min Act: -0.0000

Data Index: 448634 (The Pile)

Max Activating Token Index: 1009