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

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

Neuron 2101 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0668. Min Range: -1.0668

Max Act: 1.0668. Min Act: -0.0001

Data Index: 335266 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9621. Min Act: -0.0001

Data Index: 424079 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 1.0668. Min Range: -1.0668

Max Act: 1.0111. Min Act: -0.0001

Data Index: 217291 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9298. Min Act: -0.0001

Data Index: 1141198 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9277. Min Act: -0.0001

Data Index: 1048026 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9191. Min Act: -0.0001

Data Index: 473529 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8973. Min Act: -0.0001

Data Index: 73777 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9242. Min Act: -0.0001

Data Index: 142000 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9086. Min Act: -0.0001

Data Index: 697062 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8367. Min Act: -0.0001

Data Index: 292171 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7707. Min Act: -0.0001

Data Index: 474372 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7605. Min Act: -0.0001

Data Index: 1214803 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8097. Min Act: -0.0001

Data Index: 458263 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8323. Min Act: -0.0001

Data Index: 779952 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8488. Min Act: -0.0001

Data Index: 1125678 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7743. Min Act: -0.0001

Data Index: 968009 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7529. Min Act: -0.0001

Data Index: 753575 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7873. Min Act: -0.0001

Data Index: 23400 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8052. Min Act: -0.0001

Data Index: 6766 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7162. Min Act: -0.0001

Data Index: 1295740 (C4 (Web Text))

Max Activating Token Index: 681