Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2770 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.4247. Min Range: -4.4247

Max Act: 4.4247. Min Act: -0.0000

Data Index: 489434 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 4.4247. Min Range: -4.4247

Max Act: 4.0183. Min Act: -0.0000

Data Index: 121769 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 4.4247. Min Range: -4.4247

Max Act: 4.1351. Min Act: -0.0000

Data Index: 663350 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.7289. Min Act: -0.0000

Data Index: 1069035 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.8397. Min Act: -0.0000

Data Index: 1483730 (Python Code)

Max Activating Token Index: 699

Text #5

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.5908. Min Act: -0.0000

Data Index: 1543817 (Python Code)

Max Activating Token Index: 645

Text #6

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.7835. Min Act: -0.0000

Data Index: 1276546 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.5835. Min Act: -0.0000

Data Index: 679163 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.5999. Min Act: -0.0000

Data Index: 1558212 (Python Code)

Max Activating Token Index: 560

Text #9

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.3759. Min Act: -0.0000

Data Index: 1054916 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.3764. Min Act: -0.0000

Data Index: 1542249 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.2461. Min Act: -0.0000

Data Index: 942683 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.3520. Min Act: -0.0000

Data Index: 950395 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.3356. Min Act: -0.0000

Data Index: 1518879 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.4660. Min Act: -0.0000

Data Index: 931046 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.1591. Min Act: -0.0000

Data Index: 1413869 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.4002. Min Act: -0.0000

Data Index: 1281741 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.1165. Min Act: -0.0000

Data Index: 1406422 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.2320. Min Act: -0.0000

Data Index: 1052288 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 4.4247. Min Range: -4.4247

Max Act: 3.2019. Min Act: -0.0000

Data Index: 1099871 (C4 (Web Text))

Max Activating Token Index: 32