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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 523 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.7934. Min Act: -0.0000

Data Index: 283968 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.6968. Min Act: -0.0000

Data Index: 719665 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.6266. Min Act: -0.0000

Data Index: 897836 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.5125. Min Act: -0.0000

Data Index: 911228 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.5044. Min Act: -0.0000

Data Index: 604102 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.4096. Min Act: -0.0000

Data Index: 520727 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.3833. Min Act: -0.0000

Data Index: 847078 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.2077. Min Act: -0.0000

Data Index: 305564 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.2118. Min Act: -0.0000

Data Index: 963449 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.1845. Min Act: -0.0000

Data Index: 120535 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1007259 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.1621. Min Act: -0.0000

Data Index: 241255 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.1431. Min Act: -0.0000

Data Index: 496542 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.0660. Min Act: -0.0000

Data Index: 250822 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 1.7934. Min Range: -1.7934

Max Act: 1.0120. Min Act: -0.0000

Data Index: 789387 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.7934. Min Range: -1.7934

Max Act: 0.9673. Min Act: -0.0000

Data Index: 923229 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 1.7934. Min Range: -1.7934

Max Act: 0.9635. Min Act: -0.0000

Data Index: 287121 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.7934. Min Range: -1.7934

Max Act: 0.9770. Min Act: -0.0000

Data Index: 521453 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.7934. Min Range: -1.7934

Max Act: 0.9533. Min Act: -0.0000

Data Index: 827048 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.7934. Min Range: -1.7934

Max Act: 0.9840. Min Act: -0.0000

Data Index: 397828 (C4 (Web Text))

Max Activating Token Index: 352