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

Dataset: The Pile

Neuron 690 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2799. Min Range: -1.2799

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1109410 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 1.2799. Min Range: -1.2799

Max Act: 1.1088. Min Act: -0.0000

Data Index: 9109 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 1.2799. Min Range: -1.2799

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1390007 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 1.2799. Min Range: -1.2799

Max Act: 1.0669. Min Act: -0.0000

Data Index: 270811 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 1.2799. Min Range: -1.2799

Max Act: 1.1220. Min Act: -0.0000

Data Index: 1266886 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 1.2799. Min Range: -1.2799

Max Act: 1.1173. Min Act: -0.0000

Data Index: 71471 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.9906. Min Act: -0.0000

Data Index: 987352 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.9577. Min Act: -0.0000

Data Index: 154371 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.8140. Min Act: -0.0000

Data Index: 195572 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.8986. Min Act: -0.0000

Data Index: 470133 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.8580. Min Act: -0.0000

Data Index: 90222 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1085136 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.8664. Min Act: -0.0000

Data Index: 482822 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1629077 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 1.2799. Min Range: -1.2799

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1331618 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1275051 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 1.2799. Min Range: -1.2799

Max Act: 1.0051. Min Act: -0.0000

Data Index: 901807 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1718234 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.8500. Min Act: -0.0000

Data Index: 998509 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.2799. Min Range: -1.2799

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1396888 (The Pile)

Max Activating Token Index: 969