Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2488 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2701. Min Act: -0.0000

Data Index: 968252 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1596121 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2561. Min Act: -0.0000

Data Index: 517044 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2417. Min Act: -0.0000

Data Index: 294062 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1078829 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2430. Min Act: -0.0000

Data Index: 494583 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2313. Min Act: -0.0001

Data Index: 1517747 (Python Code)

Max Activating Token Index: 780

Text #7

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2398. Min Act: -0.0001

Data Index: 1549741 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2296. Min Act: -0.0001

Data Index: 1440186 (Python Code)

Max Activating Token Index: 519

Text #9

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1571174 (Python Code)

Max Activating Token Index: 372

Text #10

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1000836 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1566380 (Python Code)

Max Activating Token Index: 819

Text #12

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2141. Min Act: -0.0001

Data Index: 1652454 (Python Code)

Max Activating Token Index: 229

Text #13

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2260. Min Act: -0.0000

Data Index: 177075 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2149. Min Act: -0.0001

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1301536 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1632542 (Python Code)

Max Activating Token Index: 429

Text #17

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1591300 (Python Code)

Max Activating Token Index: 637

Text #18

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2096. Min Act: -0.0000

Data Index: 732933 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2153. Min Act: -0.0000

Data Index: 900952 (C4 (Web Text))

Max Activating Token Index: 102