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

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

Neuron 4070 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: 6.6258. Min Range: -6.6258

Max Act: 6.6258. Min Act: -0.0000

Data Index: 427321 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 6.6258. Min Range: -6.6258

Max Act: 6.0279. Min Act: -0.0000

Data Index: 475887 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.5634. Min Act: -0.0000

Data Index: 1335631 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.6970. Min Act: -0.0000

Data Index: 1262298 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.3260. Min Act: -0.0000

Data Index: 587989 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.4516. Min Act: -0.0000

Data Index: 1176193 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.5952. Min Act: -0.0000

Data Index: 352814 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.3468. Min Act: -0.0000

Data Index: 1249378 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.1417. Min Act: -0.0000

Data Index: 990377 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.2460. Min Act: -0.0000

Data Index: 1211579 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.0088. Min Act: -0.0000

Data Index: 1255577 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.0876. Min Act: -0.0000

Data Index: 931034 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.0710. Min Act: -0.0000

Data Index: 178448 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.1628. Min Act: -0.0000

Data Index: 876867 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 6.6258. Min Range: -6.6258

Max Act: 4.8358. Min Act: -0.0000

Data Index: 923386 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 6.6258. Min Range: -6.6258

Max Act: 4.7938. Min Act: -0.0000

Data Index: 222112 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 6.6258. Min Range: -6.6258

Max Act: 4.8090. Min Act: -0.0000

Data Index: 267444 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 6.6258. Min Range: -6.6258

Max Act: 5.0902. Min Act: -0.0000

Data Index: 876843 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 6.6258. Min Range: -6.6258

Max Act: 4.7495. Min Act: -0.0000

Data Index: 106684 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 6.6258. Min Range: -6.6258

Max Act: 4.5323. Min Act: -0.0000

Data Index: 347817 (C4 (Web Text))

Max Activating Token Index: 343