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

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

Neuron 985 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.8760. Min Act: -0.0001

Data Index: 835556 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.8111. Min Act: -0.0001

Data Index: 1055171 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.7495. Min Act: -0.0001

Data Index: 957196 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.4277. Min Act: -0.0001

Data Index: 682375 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.5680. Min Act: -0.0001

Data Index: 814882 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.5473. Min Act: -0.0001

Data Index: 583467 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.5824. Min Act: -0.0001

Data Index: 1116694 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.5983. Min Act: -0.0001

Data Index: 413067 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.6577. Min Act: -0.0001

Data Index: 1246015 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.5944. Min Act: -0.0001

Data Index: 1182889 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.4150. Min Act: -0.0001

Data Index: 229482 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.4510. Min Act: -0.0001

Data Index: 956477 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.4838. Min Act: -0.0001

Data Index: 700392 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.4493. Min Act: -0.0001

Data Index: 266530 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.4036. Min Act: -0.0001

Data Index: 829648 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.4118. Min Act: -0.0001

Data Index: 1131013 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.3383. Min Act: -0.0001

Data Index: 1608356 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.4124. Min Act: -0.0001

Data Index: 1157902 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.3063. Min Act: -0.0001

Data Index: 800156 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.8760. Min Range: -1.8760

Max Act: 1.3033. Min Act: -0.0001

Data Index: 1243521 (C4 (Web Text))

Max Activating Token Index: 413