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

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

Neuron 1238 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: 0.8114. Min Range: -0.8114

Max Act: 0.8114. Min Act: -0.0000

Data Index: 721808 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.5714. Min Act: -0.0000

Data Index: 118325 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1650508 (Python Code)

Max Activating Token Index: 922

Text #3

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.6807. Min Act: -0.0000

Data Index: 377640 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4995. Min Act: -0.0000

Data Index: 395409 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1417040 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1084078 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1651624 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.5408. Min Act: -0.0000

Data Index: 357491 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4648. Min Act: -0.0000

Data Index: 633387 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1610952 (Python Code)

Max Activating Token Index: 359

Text #11

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1500152 (Python Code)

Max Activating Token Index: 588

Text #12

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1485388 (Python Code)

Max Activating Token Index: 485

Text #13

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1360696 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1057462 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1026199 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4020. Min Act: -0.0000

Data Index: 489929 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1085274 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1506393 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 0.8114. Min Range: -0.8114

Max Act: 0.3739. Min Act: -0.0000

Data Index: 423414 (C4 (Web Text))

Max Activating Token Index: 126