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

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

Neuron 499 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.7710. Min Act: -0.0000

Data Index: 83327 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.4379. Min Act: -0.0000

Data Index: 1226265 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1213597 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.4370. Min Act: -0.0000

Data Index: 393094 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3060. Min Act: -0.0000

Data Index: 396671 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2700. Min Act: -0.0000

Data Index: 1325242 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2628. Min Act: -0.0000

Data Index: 786988 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1940. Min Act: -0.0000

Data Index: 1265655 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1685. Min Act: -0.0000

Data Index: 24718 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1640. Min Act: -0.0000

Data Index: 126689 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1355467 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1864. Min Act: -0.0000

Data Index: 144749 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0943. Min Act: -0.0000

Data Index: 635938 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1118. Min Act: -0.0000

Data Index: 434411 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1099023 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0403. Min Act: -0.0000

Data Index: 822530 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1180282 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1182690 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1239125 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1079457 (C4 (Web Text))

Max Activating Token Index: 866