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

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

Neuron 4622 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.2873. Min Act: -0.0000

Data Index: 552186 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1475. Min Act: -0.0000

Data Index: 854306 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1876. Min Act: -0.0000

Data Index: 647015 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0845. Min Act: -0.0000

Data Index: 846614 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1354. Min Act: -0.0000

Data Index: 664996 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1138. Min Act: -0.0000

Data Index: 214137 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0362. Min Act: -0.0000

Data Index: 834801 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9929. Min Act: -0.0000

Data Index: 542270 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1351447 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1179095 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9437. Min Act: -0.0000

Data Index: 48936 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1077007 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.8422. Min Act: -0.0000

Data Index: 597264 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.8973. Min Act: -0.0000

Data Index: 310132 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9186. Min Act: -0.0000

Data Index: 970941 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9072. Min Act: -0.0000

Data Index: 911970 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.8774. Min Act: -0.0000

Data Index: 656 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.8281. Min Act: -0.0000

Data Index: 779898 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9028. Min Act: -0.0000

Data Index: 14487 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1021496 (C4 (Web Text))

Max Activating Token Index: 47