Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6116 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4076. Min Range: -2.4076

Max Act: 2.4076. Min Act: -0.0001

Data Index: 95914 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.8324. Min Act: -0.0000

Data Index: 1332687 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.7717. Min Act: -0.0001

Data Index: 731419 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.8494. Min Act: -0.0000

Data Index: 722650 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 2.4076. Min Range: -2.4076

Max Act: 2.0218. Min Act: -0.0001

Data Index: 792163 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.7932. Min Act: -0.0000

Data Index: 483705 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.9031. Min Act: -0.0000

Data Index: 787484 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.8387. Min Act: -0.0001

Data Index: 481698 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.6826. Min Act: -0.0000

Data Index: 823015 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.8134. Min Act: -0.0000

Data Index: 555644 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.9779. Min Act: -0.0000

Data Index: 645772 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.7687. Min Act: -0.0000

Data Index: 993842 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.6681. Min Act: -0.0001

Data Index: 1076232 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.8312. Min Act: -0.0000

Data Index: 1002011 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.5432. Min Act: -0.0000

Data Index: 1213878 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.6888. Min Act: -0.0001

Data Index: 1284254 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.5969. Min Act: -0.0000

Data Index: 294119 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.4925. Min Act: -0.0000

Data Index: 737575 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.5926. Min Act: -0.0000

Data Index: 574448 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 2.4076. Min Range: -2.4076

Max Act: 1.4996. Min Act: -0.0001

Data Index: 452079 (C4 (Web Text))

Max Activating Token Index: 477