Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 99 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1320. Min Act: -0.0001

Data Index: 685893 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1215. Min Act: -0.0001

Data Index: 19826 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1153. Min Act: -0.0001

Data Index: 710476 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1157065 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1062. Min Act: -0.0001

Data Index: 754006 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1222870 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1051. Min Act: -0.0001

Data Index: 756956 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0901. Min Act: -0.0001

Data Index: 990836 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0999. Min Act: -0.0001

Data Index: 787286 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1033. Min Act: -0.0001

Data Index: 16590 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0916. Min Act: -0.0001

Data Index: 491619 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1019. Min Act: -0.0001

Data Index: 700383 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1332550 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1015. Min Act: -0.0001

Data Index: 116544 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1040. Min Act: -0.0001

Data Index: 995159 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0966. Min Act: -0.0001

Data Index: 324884 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0923. Min Act: -0.0001

Data Index: 839800 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1204080 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0925. Min Act: -0.0001

Data Index: 796730 (C4 (Web Text))

Max Activating Token Index: 110