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

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

Neuron 1264 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1398975 (Python Code)

Max Activating Token Index: 196

Text #1

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1456999 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1653243 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1648225 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1413194 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1609655 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1452245 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1631253 (Python Code)

Max Activating Token Index: 666

Text #8

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1595144 (Python Code)

Max Activating Token Index: 241

Text #9

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1369095 (Python Code)

Max Activating Token Index: 819

Text #10

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1362736 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1395411 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1375533 (Python Code)

Max Activating Token Index: 94

Text #13

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1408752 (Python Code)

Max Activating Token Index: 782

Text #14

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1540880 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1638571 (Python Code)

Max Activating Token Index: 247

Text #16

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1560048 (Python Code)

Max Activating Token Index: 745

Text #17

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1605300 (Python Code)

Max Activating Token Index: 859

Text #18

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1421905 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1379726 (Python Code)

Max Activating Token Index: 694