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

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

Neuron 3072 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1034766 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.7638. Min Act: -0.0000

Data Index: 753415 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.7454. Min Act: -0.0000

Data Index: 733071 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.7539. Min Act: -0.0000

Data Index: 825232 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.7235. Min Act: -0.0000

Data Index: 335955 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6991. Min Act: -0.0000

Data Index: 263783 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6879. Min Act: -0.0000

Data Index: 264003 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6365. Min Act: -0.0000

Data Index: 593274 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1145029 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6876. Min Act: 0.0000

Data Index: 1223481 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6658. Min Act: -0.0000

Data Index: 383621 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1262329 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6342. Min Act: -0.0000

Data Index: 756509 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6277. Min Act: -0.0000

Data Index: 861551 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1216493 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6280. Min Act: -0.0000

Data Index: 801381 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6152. Min Act: -0.0000

Data Index: 692464 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6553. Min Act: -0.0000

Data Index: 412006 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1108574 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6131. Min Act: -0.0000

Data Index: 207983 (C4 (Web Text))

Max Activating Token Index: 604