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

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

Neuron 551 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.7531. Min Act: -0.0001

Data Index: 1559318 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4637. Min Act: -0.0001

Data Index: 1591580 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4056. Min Act: -0.0001

Data Index: 1395244 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.4002. Min Act: -0.0001

Data Index: 1651621 (Python Code)

Max Activating Token Index: 762

Text #4

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.1928. Min Act: -0.0001

Data Index: 1579037 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.2891. Min Act: -0.0001

Data Index: 1530591 (Python Code)

Max Activating Token Index: 529

Text #6

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.2013. Min Act: -0.0001

Data Index: 1570571 (Python Code)

Max Activating Token Index: 228

Text #7

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.0545. Min Act: -0.0001

Data Index: 1441299 (Python Code)

Max Activating Token Index: 777

Text #8

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.0367. Min Act: -0.0001

Data Index: 1388574 (Python Code)

Max Activating Token Index: 311

Text #9

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.1494. Min Act: -0.0001

Data Index: 1583159 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 3.7531. Min Range: -3.7531

Max Act: 2.8560. Min Act: -0.0001

Data Index: 1582693 (Python Code)

Max Activating Token Index: 766

Text #11

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.3943. Min Act: -0.0001

Data Index: 1590993 (Python Code)

Max Activating Token Index: 520

Text #12

Max Range: 3.7531. Min Range: -3.7531

Max Act: 2.9553. Min Act: -0.0001

Data Index: 1501844 (Python Code)

Max Activating Token Index: 881

Text #13

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.0885. Min Act: -0.0001

Data Index: 1409493 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.0590. Min Act: -0.0001

Data Index: 1427122 (Python Code)

Max Activating Token Index: 415

Text #15

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.0729. Min Act: -0.0001

Data Index: 1605235 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.0401. Min Act: -0.0001

Data Index: 1364799 (Python Code)

Max Activating Token Index: 317

Text #17

Max Range: 3.7531. Min Range: -3.7531

Max Act: 2.8966. Min Act: -0.0001

Data Index: 1613362 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 3.7531. Min Range: -3.7531

Max Act: 3.3014. Min Act: -0.0001

Data Index: 1514900 (Python Code)

Max Activating Token Index: 1015

Text #19

Max Range: 3.7531. Min Range: -3.7531

Max Act: 2.8666. Min Act: -0.0001

Data Index: 1652257 (Python Code)

Max Activating Token Index: 808