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

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

Neuron 1578 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: 0.5166. Min Range: -0.5166

Max Act: 0.5166. Min Act: -0.0002

Data Index: 384619 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.5115. Min Act: -0.0002

Data Index: 45964 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.5017. Min Act: -0.0002

Data Index: 1292197 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4927. Min Act: -0.0002

Data Index: 1293170 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4860. Min Act: -0.0002

Data Index: 125033 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4765. Min Act: -0.0003

Data Index: 828521 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4767. Min Act: -0.0002

Data Index: 501186 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4660. Min Act: -0.0003

Data Index: 259766 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4630. Min Act: -0.0002

Data Index: 369038 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4541. Min Act: -0.0002

Data Index: 1353955 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4468. Min Act: -0.0002

Data Index: 14010 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4464. Min Act: -0.0003

Data Index: 304077 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4455. Min Act: -0.0002

Data Index: 350201 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4408. Min Act: -0.0002

Data Index: 1039786 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4388. Min Act: -0.0002

Data Index: 891326 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4357. Min Act: -0.0002

Data Index: 67258 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4418. Min Act: -0.0002

Data Index: 1115446 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4313. Min Act: -0.0002

Data Index: 97785 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4479. Min Act: -0.0003

Data Index: 124618 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4340. Min Act: -0.0003

Data Index: 1347957 (C4 (Web Text))

Max Activating Token Index: 634