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

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

Neuron 1799 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0056. Min Range: -1.0056

Max Act: 1.0056. Min Act: -0.0000

Data Index: 803164 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1583120 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1197946 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8128. Min Act: -0.0000

Data Index: 130961 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1395237 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1482475 (Python Code)

Max Activating Token Index: 1021

Text #6

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7916. Min Act: -0.0000

Data Index: 102441 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7396. Min Act: -0.0000

Data Index: 124023 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1079320 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7784. Min Act: -0.0000

Data Index: 428291 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7266. Min Act: -0.0000

Data Index: 972271 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6447. Min Act: -0.0000

Data Index: 492198 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6957. Min Act: -0.0000

Data Index: 490029 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1380013 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7623. Min Act: -0.0000

Data Index: 341318 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1086676 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6933. Min Act: -0.0000

Data Index: 564066 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6891. Min Act: -0.0000

Data Index: 709683 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7000. Min Act: -0.0000

Data Index: 564713 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6686. Min Act: -0.0000

Data Index: 740089 (C4 (Web Text))

Max Activating Token Index: 953