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

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

Neuron 1978 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1393122 (Python Code)

Max Activating Token Index: 1008

Text #1

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1136254 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5521. Min Act: -0.0000

Data Index: 963303 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5215. Min Act: -0.0000

Data Index: 462031 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1565870 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4907. Min Act: -0.0000

Data Index: 611771 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1602231 (Python Code)

Max Activating Token Index: 898

Text #7

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4576. Min Act: -0.0000

Data Index: 199711 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1342333 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1185130 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1220052 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1492079 (Python Code)

Max Activating Token Index: 544

Text #12

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4144. Min Act: -0.0000

Data Index: 504245 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4452. Min Act: -0.0000

Data Index: 320622 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.3835. Min Act: -0.0000

Data Index: 176923 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1432504 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1401068 (Python Code)

Max Activating Token Index: 848

Text #17

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1573819 (Python Code)

Max Activating Token Index: 952

Text #18

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1425853 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1467363 (Python Code)

Max Activating Token Index: 596