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

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

Neuron 1198 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.8056. Min Act: -0.0002

Data Index: 1149509 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.8049. Min Act: -0.0002

Data Index: 349226 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7906. Min Act: -0.0002

Data Index: 559754 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7692. Min Act: -0.0002

Data Index: 107885 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7712. Min Act: -0.0003

Data Index: 1025571 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7739. Min Act: -0.0002

Data Index: 481050 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7517. Min Act: -0.0002

Data Index: 522196 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7643. Min Act: -0.0002

Data Index: 307670 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7451. Min Act: -0.0002

Data Index: 1178637 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7416. Min Act: -0.0002

Data Index: 282107 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7520. Min Act: -0.0002

Data Index: 110460 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7637. Min Act: -0.0002

Data Index: 76645 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7467. Min Act: -0.0002

Data Index: 827040 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7564. Min Act: -0.0002

Data Index: 1322244 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7487. Min Act: -0.0002

Data Index: 485015 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7236. Min Act: -0.0002

Data Index: 701674 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7189. Min Act: -0.0002

Data Index: 805939 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7221. Min Act: -0.0002

Data Index: 174483 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7065. Min Act: -0.0002

Data Index: 1077858 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7289. Min Act: -0.0003

Data Index: 1348683 (C4 (Web Text))

Max Activating Token Index: 480