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

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

Neuron 2074 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.9024. Min Act: 0.0000

Data Index: 316341 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.8280. Min Act: 0.0000

Data Index: 1114035 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7714. Min Act: -0.0000

Data Index: 254432 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7568. Min Act: 0.0000

Data Index: 258010 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7587. Min Act: -0.0000

Data Index: 339380 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7320. Min Act: 0.0000

Data Index: 1266032 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6893. Min Act: 0.0000

Data Index: 727971 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6727. Min Act: 0.0000

Data Index: 746784 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6627. Min Act: -0.0000

Data Index: 811889 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6266. Min Act: 0.0000

Data Index: 1283438 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5463. Min Act: 0.0000

Data Index: 909176 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5749. Min Act: -0.0000

Data Index: 481997 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5712. Min Act: -0.0000

Data Index: 962929 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5690. Min Act: 0.0002

Data Index: 93088 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5591. Min Act: 0.0000

Data Index: 430105 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1181245 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5701. Min Act: -0.0000

Data Index: 324145 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5681. Min Act: -0.0000

Data Index: 56238 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1050769 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5323. Min Act: 0.0000

Data Index: 983711 (C4 (Web Text))

Max Activating Token Index: 41