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

Dataset: The Pile

Neuron 2235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1415814 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4595. Min Act: -0.0000

Data Index: 371984 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4807. Min Act: -0.0000

Data Index: 355039 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4332. Min Act: -0.0000

Data Index: 52668 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4306. Min Act: -0.0000

Data Index: 387866 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1244937 (The Pile)

Max Activating Token Index: 514

Text #6

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1138065 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4097. Min Act: -0.0000

Data Index: 209051 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1735919 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1017276 (The Pile)

Max Activating Token Index: 488

Text #10

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4019. Min Act: -0.0000

Data Index: 548312 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1696899 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4435. Min Act: -0.0000

Data Index: 887965 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1741490 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1975882 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3968. Min Act: -0.0000

Data Index: 593042 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1603162 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4067. Min Act: -0.0000

Data Index: 398626 (The Pile)

Max Activating Token Index: 216

Text #18

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4411. Min Act: -0.0000

Data Index: 615852 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1634525 (The Pile)

Max Activating Token Index: 518