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

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

Neuron 2847 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0789. Min Range: -1.0789

Max Act: 1.0789. Min Act: -0.0000

Data Index: 175717 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.0789. Min Range: -1.0789

Max Act: 1.0690. Min Act: -0.0000

Data Index: 358816 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.9401. Min Act: -0.0000

Data Index: 502512 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1246069 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 1.0789. Min Range: -1.0789

Max Act: 1.0153. Min Act: -0.0000

Data Index: 926738 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.9321. Min Act: -0.0000

Data Index: 271236 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8792. Min Act: -0.0000

Data Index: 57368 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1045573 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8852. Min Act: 0.0000

Data Index: 226191 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8737. Min Act: 0.0001

Data Index: 14486 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8650. Min Act: -0.0000

Data Index: 645128 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1274498 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8569. Min Act: 0.0000

Data Index: 1268113 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1348608 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8365. Min Act: -0.0000

Data Index: 93755 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8148. Min Act: 0.0000

Data Index: 1107260 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8117. Min Act: -0.0000

Data Index: 255151 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1338077 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7907. Min Act: -0.0000

Data Index: 125442 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7896. Min Act: -0.0000

Data Index: 881995 (C4 (Web Text))

Max Activating Token Index: 982