Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3005 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.8401. Min Act: -0.0000

Data Index: 793162 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7915. Min Act: -0.0000

Data Index: 624474 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1003282 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7519. Min Act: -0.0000

Data Index: 249435 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1181479 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1600325 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1148636 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1385904 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1262914 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1463182 (Python Code)

Max Activating Token Index: 33

Text #10

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1619292 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1154973 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6357. Min Act: -0.0000

Data Index: 613297 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1629832 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1440846 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1019378 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1585045 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6090. Min Act: -0.0000

Data Index: 910968 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1632997 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1536187 (Python Code)

Max Activating Token Index: 20