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

Dataset: The Pile

Neuron 105 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: 1.0004. Min Range: -1.0004

Max Act: 1.0004. Min Act: -0.0000

Data Index: 221471 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1757365 (The Pile)

Max Activating Token Index: 268

Text #2

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.8070. Min Act: -0.0000

Data Index: 544257 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1879542 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7054. Min Act: -0.0000

Data Index: 888524 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1281343 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1911550 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6698. Min Act: -0.0000

Data Index: 467620 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1472470 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1114793 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1974260 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1433467 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7161. Min Act: -0.0000

Data Index: 923676 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1418549 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1343991 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6784. Min Act: -0.0000

Data Index: 224239 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1617191 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1857965 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1986707 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1894696 (The Pile)

Max Activating Token Index: 791