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

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

Neuron 2190 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.6271. Min Act: -0.0001

Data Index: 91381 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5691. Min Act: -0.0001

Data Index: 227530 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1268390 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5991. Min Act: -0.0001

Data Index: 177696 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1558296 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5073. Min Act: -0.0000

Data Index: 876467 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5301. Min Act: -0.0000

Data Index: 907572 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1423378 (Python Code)

Max Activating Token Index: 649

Text #8

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1001622 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1489876 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1496359 (Python Code)

Max Activating Token Index: 636

Text #11

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1415895 (Python Code)

Max Activating Token Index: 320

Text #12

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4382. Min Act: -0.0001

Data Index: 1376254 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1465317 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1568411 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5172. Min Act: -0.0001

Data Index: 1650526 (Python Code)

Max Activating Token Index: 912

Text #16

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4966. Min Act: -0.0001

Data Index: 161913 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1641230 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1458630 (Python Code)

Max Activating Token Index: 746

Text #19

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1391471 (Python Code)

Max Activating Token Index: 33