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

Dataset: The Pile

Neuron 3386 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.5052. Min Act: -0.0000

Data Index: 1112256 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1224446 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2248. Min Act: -0.0000

Data Index: 263306 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1914361 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2478. Min Act: -0.0000

Data Index: 374380 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2712. Min Act: -0.0000

Data Index: 1234602 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1682. Min Act: -0.0000

Data Index: 1029372 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1330095 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0924. Min Act: -0.0000

Data Index: 132030 (The Pile)

Max Activating Token Index: 104

Text #9

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1198. Min Act: -0.0000

Data Index: 651397 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0992. Min Act: -0.0000

Data Index: 670288 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1156. Min Act: -0.0000

Data Index: 374662 (The Pile)

Max Activating Token Index: 831

Text #12

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1636495 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1646849 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1433995 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1441919 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1802. Min Act: -0.0000

Data Index: 405592 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1262509 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1381663 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1534161 (The Pile)

Max Activating Token Index: 653