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

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

Neuron 1072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.9087. Min Act: -0.0000

Data Index: 360486 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1004832 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8047. Min Act: -0.0000

Data Index: 36586 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1268812 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1341780 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8062. Min Act: -0.0000

Data Index: 602720 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7518. Min Act: -0.0000

Data Index: 878483 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1093243 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7819. Min Act: -0.0000

Data Index: 29101 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1213018 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7892. Min Act: -0.0000

Data Index: 402240 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7239. Min Act: -0.0000

Data Index: 681099 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1079091 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1322545 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7262. Min Act: -0.0000

Data Index: 435962 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6750. Min Act: -0.0000

Data Index: 776044 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7162. Min Act: -0.0000

Data Index: 600581 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1315464 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6916. Min Act: -0.0000

Data Index: 940496 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6599. Min Act: -0.0000

Data Index: 590928 (C4 (Web Text))

Max Activating Token Index: 858