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

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

Neuron 3188 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5670. Min Range: -4.5670

Max Act: 4.5670. Min Act: -0.0000

Data Index: 413947 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 4.5670. Min Range: -4.5670

Max Act: 4.0479. Min Act: -0.0000

Data Index: 518988 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 4.5670. Min Range: -4.5670

Max Act: 4.3376. Min Act: -0.0000

Data Index: 1611553 (Python Code)

Max Activating Token Index: 691

Text #3

Max Range: 4.5670. Min Range: -4.5670

Max Act: 4.2390. Min Act: -0.0000

Data Index: 873939 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 4.5670. Min Range: -4.5670

Max Act: 3.7660. Min Act: -0.0000

Data Index: 1508838 (Python Code)

Max Activating Token Index: 556

Text #5

Max Range: 4.5670. Min Range: -4.5670

Max Act: 3.3312. Min Act: 0.0000

Data Index: 366222 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.9415. Min Act: 0.0000

Data Index: 1299176 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 4.5670. Min Range: -4.5670

Max Act: 3.1328. Min Act: -0.0000

Data Index: 384042 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.5334. Min Act: -0.0000

Data Index: 1120415 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.6333. Min Act: -0.0000

Data Index: 1032135 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.7025. Min Act: -0.0000

Data Index: 1195739 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.6744. Min Act: -0.0000

Data Index: 1047638 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.5197. Min Act: -0.0000

Data Index: 912600 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.5284. Min Act: 0.0000

Data Index: 187807 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.6040. Min Act: 0.0000

Data Index: 227837 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.7431. Min Act: -0.0000

Data Index: 764803 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.4583. Min Act: -0.0000

Data Index: 1077969 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.7051. Min Act: -0.0000

Data Index: 278303 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.5590. Min Act: 0.0000

Data Index: 470197 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 4.5670. Min Range: -4.5670

Max Act: 2.5431. Min Act: -0.0000

Data Index: 1320822 (C4 (Web Text))

Max Activating Token Index: 165