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

Dataset: The Pile

Neuron 2182 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1926183 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1599914 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.8068. Min Act: -0.0000

Data Index: 97319 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.8513. Min Act: -0.0000

Data Index: 618879 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1130875 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1991676 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1953154 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6953. Min Act: -0.0000

Data Index: 311511 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6756. Min Act: -0.0000

Data Index: 112963 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6931. Min Act: -0.0000

Data Index: 991958 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1161747 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1732579 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6866. Min Act: -0.0000

Data Index: 617317 (The Pile)

Max Activating Token Index: 358

Text #13

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6851. Min Act: -0.0000

Data Index: 120771 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6806. Min Act: -0.0000

Data Index: 863393 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6538. Min Act: -0.0000

Data Index: 736387 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6747. Min Act: -0.0000

Data Index: 146901 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6981. Min Act: -0.0000

Data Index: 882986 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6705. Min Act: -0.0000

Data Index: 922669 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 0.8513. Min Range: -0.8513

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1124640 (The Pile)

Max Activating Token Index: 266