Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1120 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1024627 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: -0.0000

Data Index: 806752 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1053. Min Act: -0.0000

Data Index: 183610 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1130. Min Act: -0.0000

Data Index: 552577 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0933. Min Act: -0.0000

Data Index: 366194 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0918. Min Act: -0.0000

Data Index: 286537 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1043229 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1420965 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1025493 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0927. Min Act: -0.0000

Data Index: 520889 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0928. Min Act: -0.0000

Data Index: 805941 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0849. Min Act: -0.0000

Data Index: 631589 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0839. Min Act: -0.0000

Data Index: 564759 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1272920 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1031519 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0831. Min Act: -0.0000

Data Index: 955021 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0875. Min Act: -0.0000

Data Index: 258569 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1006554 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1059336 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0814. Min Act: -0.0000

Data Index: 157995 (C4 (Web Text))

Max Activating Token Index: 453