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

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

Neuron 2093 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.7895. Min Act: 0.0000

Data Index: 456313 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5020. Min Act: -0.0000

Data Index: 429643 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5184. Min Act: 0.0000

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5055. Min Act: 0.0000

Data Index: 172620 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.4147. Min Act: -0.0000

Data Index: 469048 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5832. Min Act: -0.0000

Data Index: 417868 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.4772. Min Act: -0.0000

Data Index: 600484 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.4351. Min Act: -0.0000

Data Index: 859454 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.4415. Min Act: 0.0000

Data Index: 75195 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3691. Min Act: -0.0000

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1061429 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3505. Min Act: -0.0000

Data Index: 397184 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1310128 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1023838 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1082743 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.4119. Min Act: -0.0000

Data Index: 995094 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.4621. Min Act: -0.0000

Data Index: 1357009 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.2246. Min Act: -0.0000

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.2907. Min Act: -0.0000

Data Index: 312502 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.2920. Min Act: -0.0000

Data Index: 885590 (C4 (Web Text))

Max Activating Token Index: 880