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

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

Neuron 1065 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.7372. Min Act: -0.0000

Data Index: 292290 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5102. Min Act: -0.0001

Data Index: 1630309 (Python Code)

Max Activating Token Index: 319

Text #2

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5022. Min Act: -0.0000

Data Index: 584088 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1247396 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1455385 (Python Code)

Max Activating Token Index: 324

Text #5

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1408015 (Python Code)

Max Activating Token Index: 298

Text #6

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5278. Min Act: -0.0000

Data Index: 622773 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5411. Min Act: -0.0000

Data Index: 880981 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5135. Min Act: -0.0000

Data Index: 879204 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1208665 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4945. Min Act: -0.0000

Data Index: 229207 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1408174 (Python Code)

Max Activating Token Index: 575

Text #12

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1050839 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4815. Min Act: -0.0000

Data Index: 740222 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4551. Min Act: -0.0000

Data Index: 263920 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4825. Min Act: -0.0000

Data Index: 975228 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5142. Min Act: -0.0001

Data Index: 1418038 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1213180 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4677. Min Act: -0.0001

Data Index: 1462849 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.4631. Min Act: -0.0000

Data Index: 345560 (C4 (Web Text))

Max Activating Token Index: 1013