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

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

Neuron 1667 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: 0.8945. Min Range: -0.8945

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1495886 (Python Code)

Max Activating Token Index: 524

Text #1

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1606948 (Python Code)

Max Activating Token Index: 320

Text #2

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1649080 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1360676 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1534825 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1532615 (Python Code)

Max Activating Token Index: 923

Text #6

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1515981 (Python Code)

Max Activating Token Index: 998

Text #7

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1021582 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.5109. Min Act: -0.0000

Data Index: 26051 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.4959. Min Act: -0.0000

Data Index: 99454 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1420453 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.4267. Min Act: -0.0000

Data Index: 578456 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.4078. Min Act: -0.0000

Data Index: 952886 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.4244. Min Act: -0.0000

Data Index: 413160 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.4173. Min Act: -0.0000

Data Index: 135723 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1386353 (Python Code)

Max Activating Token Index: 473

Text #16

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.4210. Min Act: -0.0000

Data Index: 55019 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1562477 (Python Code)

Max Activating Token Index: 236

Text #18

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1474879 (Python Code)

Max Activating Token Index: 472

Text #19

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.3937. Min Act: -0.0000

Data Index: 702682 (C4 (Web Text))

Max Activating Token Index: 221