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

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

Neuron 5446 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: 1.2721. Min Range: -1.2721

Max Act: 1.2721. Min Act: -0.0000

Data Index: 561110 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.2219. Min Act: -0.0001

Data Index: 671364 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1181628 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0903. Min Act: -0.0000

Data Index: 540203 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1272230 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0969. Min Act: -0.0000

Data Index: 81429 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0478. Min Act: -0.0000

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1236913 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0084. Min Act: -0.0000

Data Index: 151103 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0048. Min Act: -0.0000

Data Index: 37658 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0231. Min Act: -0.0000

Data Index: 56320 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0467. Min Act: -0.0000

Data Index: 370019 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.2721. Min Range: -1.2721

Max Act: 0.9965. Min Act: -0.0000

Data Index: 1240847 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 1.2721. Min Range: -1.2721

Max Act: 1.0306. Min Act: -0.0001

Data Index: 1089645 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.2721. Min Range: -1.2721

Max Act: 0.9641. Min Act: -0.0000

Data Index: 123672 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 1.2721. Min Range: -1.2721

Max Act: 0.9387. Min Act: -0.0000

Data Index: 183496 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.2721. Min Range: -1.2721

Max Act: 0.9860. Min Act: -0.0000

Data Index: 33141 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 1.2721. Min Range: -1.2721

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1327371 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.2721. Min Range: -1.2721

Max Act: 0.9718. Min Act: -0.0000

Data Index: 264131 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.2721. Min Range: -1.2721

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1023233 (C4 (Web Text))

Max Activating Token Index: 521