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

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

Neuron 4883 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.7674. Min Act: 0.0000

Data Index: 735235 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.7323. Min Act: -0.0000

Data Index: 962067 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.6914. Min Act: -0.0000

Data Index: 1333422 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5953. Min Act: -0.0000

Data Index: 1346498 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1052085 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5040. Min Act: 0.0000

Data Index: 1218591 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4862. Min Act: 0.0001

Data Index: 9999 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5732. Min Act: 0.0000

Data Index: 776 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5631. Min Act: 0.0000

Data Index: 1346590 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3637. Min Act: -0.0000

Data Index: 309379 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4379. Min Act: -0.0000

Data Index: 938459 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4304. Min Act: -0.0000

Data Index: 166907 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3987. Min Act: 0.0001

Data Index: 263136 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3746. Min Act: -0.0000

Data Index: 634551 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1338259 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.2592. Min Act: 0.0001

Data Index: 1053894 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3327. Min Act: 0.0001

Data Index: 216711 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3199. Min Act: 0.0000

Data Index: 271419 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1054637 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.2142. Min Act: -0.0000

Data Index: 528142 (C4 (Web Text))

Max Activating Token Index: 107