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

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

Neuron 2189 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5363. Min Range: -4.5363

Max Act: 4.5363. Min Act: -0.0000

Data Index: 755743 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 4.5363. Min Range: -4.5363

Max Act: 4.4059. Min Act: -0.0000

Data Index: 757098 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 4.5363. Min Range: -4.5363

Max Act: 4.3901. Min Act: -0.0000

Data Index: 989960 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 4.5363. Min Range: -4.5363

Max Act: 4.1295. Min Act: -0.0000

Data Index: 1184604 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.9024. Min Act: -0.0000

Data Index: 307641 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 4.5363. Min Range: -4.5363

Max Act: 4.2241. Min Act: -0.0000

Data Index: 955969 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.8692. Min Act: -0.0000

Data Index: 557876 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 4.5363. Min Range: -4.5363

Max Act: 4.0305. Min Act: -0.0000

Data Index: 168976 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.8229. Min Act: -0.0000

Data Index: 1029904 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.9207. Min Act: -0.0000

Data Index: 1055524 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.8602. Min Act: -0.0000

Data Index: 1229813 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.8489. Min Act: -0.0000

Data Index: 957526 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.8305. Min Act: -0.0000

Data Index: 474696 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.8123. Min Act: -0.0000

Data Index: 1029696 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.7891. Min Act: -0.0000

Data Index: 148550 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.8062. Min Act: -0.0000

Data Index: 287326 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.5752. Min Act: -0.0000

Data Index: 1287322 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.5490. Min Act: -0.0000

Data Index: 389120 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.7402. Min Act: -0.0000

Data Index: 6453 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 4.5363. Min Range: -4.5363

Max Act: 3.5261. Min Act: -0.0000

Data Index: 432451 (C4 (Web Text))

Max Activating Token Index: 3