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

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

Neuron 4711 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0970. Min Range: -1.0970

Max Act: 1.0970. Min Act: -0.0000

Data Index: 306309 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 1.0970. Min Range: -1.0970

Max Act: 1.0061. Min Act: -0.0000

Data Index: 664513 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1098971 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1247798 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.8955. Min Act: -0.0000

Data Index: 667508 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.6894. Min Act: -0.0000

Data Index: 564365 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.6666. Min Act: -0.0000

Data Index: 981235 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5736. Min Act: -0.0000

Data Index: 36469 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5739. Min Act: -0.0000

Data Index: 988258 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5203. Min Act: -0.0000

Data Index: 751072 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5439. Min Act: -0.0000

Data Index: 736558 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5220. Min Act: -0.0000

Data Index: 643423 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5338. Min Act: -0.0000

Data Index: 717273 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.4747. Min Act: -0.0000

Data Index: 895216 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5064. Min Act: -0.0000

Data Index: 1026727 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.4834. Min Act: -0.0000

Data Index: 48240 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5068. Min Act: -0.0000

Data Index: 721042 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.4922. Min Act: -0.0000

Data Index: 521247 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1003531 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1127380 (C4 (Web Text))

Max Activating Token Index: 185