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

Dataset: The Pile

Neuron 2669 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: 0.7453. Min Range: -0.7453

Max Act: 0.7453. Min Act: -0.0000

Data Index: 851268 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1867327 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1656917 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1791521 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5883. Min Act: -0.0000

Data Index: 919943 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1510322 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1622380 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1607613 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5704. Min Act: -0.0000

Data Index: 78466 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5463. Min Act: -0.0000

Data Index: 277305 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1411635 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5637. Min Act: -0.0000

Data Index: 344086 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1965282 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1868113 (The Pile)

Max Activating Token Index: 360

Text #14

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1101835 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1740186 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5085. Min Act: -0.0000

Data Index: 925139 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5148. Min Act: -0.0000

Data Index: 343046 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4835. Min Act: -0.0000

Data Index: 386461 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1842001 (The Pile)

Max Activating Token Index: 892