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

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

Neuron 3087 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.4232. Min Act: -0.0000

Data Index: 750931 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3725. Min Act: -0.0000

Data Index: 623449 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3708. Min Act: -0.0000

Data Index: 522469 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1622591 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3555. Min Act: -0.0000

Data Index: 714858 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3629. Min Act: -0.0000

Data Index: 91190 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3183. Min Act: -0.0000

Data Index: 613704 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3530. Min Act: -0.0000

Data Index: 311055 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3051. Min Act: -0.0000

Data Index: 765320 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1161140 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3193. Min Act: -0.0000

Data Index: 311671 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3009. Min Act: -0.0000

Data Index: 729413 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3018. Min Act: -0.0000

Data Index: 143488 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2808. Min Act: -0.0000

Data Index: 703971 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1137554 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1113510 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2755. Min Act: -0.0000

Data Index: 506558 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1101642 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2824. Min Act: -0.0000

Data Index: 541813 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1038918 (C4 (Web Text))

Max Activating Token Index: 398