Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2314 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.4946. Min Act: -0.0000

Data Index: 160324 (The Pile)

Max Activating Token Index: 810

Text #1

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.1114. Min Act: -0.0001

Data Index: 1023369 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.9931. Min Act: -0.0000

Data Index: 652649 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1930394 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.0375. Min Act: -0.0000

Data Index: 121290 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.0625. Min Act: -0.0000

Data Index: 464219 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1766442 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1328050 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1049247 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.8659. Min Act: -0.0000

Data Index: 889174 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.9273. Min Act: -0.0000

Data Index: 741903 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.8530. Min Act: -0.0000

Data Index: 332554 (The Pile)

Max Activating Token Index: 744

Text #12

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.8055. Min Act: 0.0000

Data Index: 1370833 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.8753. Min Act: -0.0000

Data Index: 138244 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.8202. Min Act: -0.0000

Data Index: 52808 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7285. Min Act: -0.0000

Data Index: 509181 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1214516 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7598. Min Act: -0.0000

Data Index: 898181 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7375. Min Act: -0.0000

Data Index: 617487 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.8667. Min Act: -0.0000

Data Index: 953903 (The Pile)

Max Activating Token Index: 1012