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

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

Neuron 917 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: 3.0590. Min Range: -3.0590

Max Act: 2.9026. Min Act: -0.0000

Data Index: 680430 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.7702. Min Act: -0.0000

Data Index: 926538 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 3.0590. Min Range: -3.0590

Max Act: 3.0590. Min Act: -0.0000

Data Index: 793863 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.7414. Min Act: -0.0000

Data Index: 981388 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.8045. Min Act: -0.0000

Data Index: 435884 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.6541. Min Act: -0.0000

Data Index: 769228 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.8007. Min Act: -0.0000

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.7812. Min Act: -0.0000

Data Index: 101405 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.7343. Min Act: -0.0000

Data Index: 1199394 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.7094. Min Act: -0.0000

Data Index: 1331633 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.5360. Min Act: -0.0000

Data Index: 518353 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.5490. Min Act: -0.0000

Data Index: 819928 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.6616. Min Act: -0.0000

Data Index: 935068 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.4556. Min Act: -0.0000

Data Index: 863915 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.4295. Min Act: -0.0000

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.4259. Min Act: -0.0000

Data Index: 117758 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.4208. Min Act: -0.0000

Data Index: 571895 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.5446. Min Act: -0.0000

Data Index: 1264215 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.3995. Min Act: -0.0000

Data Index: 20528 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 3.0590. Min Range: -3.0590

Max Act: 2.5243. Min Act: -0.0000

Data Index: 818929 (C4 (Web Text))

Max Activating Token Index: 75