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

Dataset: The Pile

Neuron 3523 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: 1.2156. Min Range: -1.2156

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1404295 (The Pile)

Max Activating Token Index: 205

Text #1

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1266757 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1243859 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1923910 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1595467 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9925. Min Act: -0.0000

Data Index: 420714 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9873. Min Act: -0.0000

Data Index: 414348 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1856542 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1494382 (The Pile)

Max Activating Token Index: 749

Text #9

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1799266 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9855. Min Act: -0.0000

Data Index: 887604 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9994. Min Act: -0.0000

Data Index: 201103 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9060. Min Act: -0.0000

Data Index: 513513 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1411092 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1904939 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8310. Min Act: -0.0000

Data Index: 838127 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8604. Min Act: -0.0000

Data Index: 992572 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8107. Min Act: -0.0000

Data Index: 600375 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1043754 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1320248 (The Pile)

Max Activating Token Index: 644