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

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

Neuron 583 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0835. Min Range: -1.0835

Max Act: 1.0835. Min Act: -0.0001

Data Index: 463699 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 1.0835. Min Range: -1.0835

Max Act: 1.0224. Min Act: -0.0001

Data Index: 60935 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9662. Min Act: -0.0001

Data Index: 665007 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9252. Min Act: -0.0000

Data Index: 150171 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.8829. Min Act: -0.0000

Data Index: 99725 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.8782. Min Act: -0.0001

Data Index: 79596 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9311. Min Act: -0.0001

Data Index: 266817 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9436. Min Act: -0.0000

Data Index: 509716 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9162. Min Act: -0.0001

Data Index: 677705 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9109. Min Act: -0.0001

Data Index: 165987 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.0835. Min Range: -1.0835

Max Act: 1.0315. Min Act: -0.0001

Data Index: 637829 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9969. Min Act: -0.0001

Data Index: 1087441 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9561. Min Act: -0.0001

Data Index: 206064 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9035. Min Act: -0.0000

Data Index: 276270 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.8112. Min Act: -0.0001

Data Index: 1220873 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.8764. Min Act: -0.0001

Data Index: 328946 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.9155. Min Act: -0.0001

Data Index: 714942 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1045874 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.7360. Min Act: -0.0001

Data Index: 1350046 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.8869. Min Act: -0.0001

Data Index: 73305 (C4 (Web Text))

Max Activating Token Index: 350