Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 995 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.9177. Min Act: -0.0000

Data Index: 612702 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.8826. Min Act: -0.0000

Data Index: 752087 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.8831. Min Act: -0.0001

Data Index: 880538 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.8471. Min Act: -0.0000

Data Index: 916486 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.9012. Min Act: -0.0000

Data Index: 30917 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.8703. Min Act: -0.0001

Data Index: 1281076 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.8757. Min Act: -0.0001

Data Index: 657160 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.9629. Min Act: -0.0001

Data Index: 378926 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.6615. Min Act: -0.0000

Data Index: 1131723 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.9472. Min Act: -0.0000

Data Index: 265212 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.8270. Min Act: -0.0001

Data Index: 751750 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.9080. Min Act: -0.0000

Data Index: 163809 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.7990. Min Act: -0.0000

Data Index: 262782 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.7994. Min Act: -0.0000

Data Index: 170833 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.8023. Min Act: -0.0000

Data Index: 1265367 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.6744. Min Act: -0.0000

Data Index: 997240 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.6776. Min Act: -0.0000

Data Index: 106262 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.7693. Min Act: -0.0000

Data Index: 1085059 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1351407 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.9629. Min Range: -1.9629

Max Act: 1.8479. Min Act: -0.0000

Data Index: 335558 (C4 (Web Text))

Max Activating Token Index: 398