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

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

Neuron 627 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: 3.8306. Min Range: -3.8306

Max Act: 3.8306. Min Act: -0.0000

Data Index: 337290 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.2623. Min Act: -0.0000

Data Index: 21702 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 3.8306. Min Range: -3.8306

Max Act: 3.0389. Min Act: -0.0000

Data Index: 1032601 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.9889. Min Act: -0.0000

Data Index: 870643 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.9306. Min Act: -0.0000

Data Index: 645676 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.8433. Min Act: -0.0000

Data Index: 254356 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.8057. Min Act: -0.0000

Data Index: 785735 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.7591. Min Act: -0.0000

Data Index: 891192 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.5450. Min Act: -0.0000

Data Index: 343350 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.4940. Min Act: -0.0000

Data Index: 223864 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.6166. Min Act: -0.0000

Data Index: 1049079 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.5940. Min Act: -0.0000

Data Index: 56198 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.7110. Min Act: -0.0000

Data Index: 99573 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.5308. Min Act: -0.0000

Data Index: 1154633 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.3292. Min Act: -0.0000

Data Index: 465375 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.4518. Min Act: -0.0000

Data Index: 385476 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.4506. Min Act: -0.0000

Data Index: 231632 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.4712. Min Act: -0.0000

Data Index: 763322 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.4615. Min Act: -0.0000

Data Index: 840949 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 3.8306. Min Range: -3.8306

Max Act: 2.4449. Min Act: -0.0000

Data Index: 1024343 (C4 (Web Text))

Max Activating Token Index: 227