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

Dataset: The Pile

Neuron 5072 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.7082. Min Act: -0.0000

Data Index: 1351846 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.6314. Min Act: -0.0000

Data Index: 1319158 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.5894. Min Act: -0.0000

Data Index: 423274 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1460940 (The Pile)

Max Activating Token Index: 816

Text #4

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.5436. Min Act: -0.0000

Data Index: 73770 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.5196. Min Act: -0.0000

Data Index: 1729801 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1606228 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3920. Min Act: -0.0000

Data Index: 1149143 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3067. Min Act: -0.0000

Data Index: 312361 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3756. Min Act: -0.0000

Data Index: 338122 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1238777 (The Pile)

Max Activating Token Index: 87

Text #11

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1598950 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3467. Min Act: -0.0000

Data Index: 1092383 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4177. Min Act: -0.0000

Data Index: 671960 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1921252 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3236. Min Act: -0.0000

Data Index: 610409 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2291. Min Act: -0.0000

Data Index: 366181 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3631. Min Act: -0.0000

Data Index: 744751 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3028. Min Act: -0.0000

Data Index: 704674 (The Pile)

Max Activating Token Index: 296

Text #19

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3540. Min Act: -0.0000

Data Index: 495604 (The Pile)

Max Activating Token Index: 205