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

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

Neuron 2987 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3816. Min Range: -2.3816

Max Act: 2.3816. Min Act: -0.0000

Data Index: 992463 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 2.3816. Min Range: -2.3816

Max Act: 2.0272. Min Act: -0.0000

Data Index: 106752 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.6878. Min Act: -0.0000

Data Index: 924378 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.7925. Min Act: -0.0000

Data Index: 776169 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1337988 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.6458. Min Act: -0.0000

Data Index: 1174498 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.7263. Min Act: -0.0000

Data Index: 533537 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.7597. Min Act: -0.0000

Data Index: 63978 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.6298. Min Act: -0.0000

Data Index: 58270 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.7160. Min Act: -0.0000

Data Index: 926950 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.6487. Min Act: -0.0000

Data Index: 60758 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1065802 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.5631. Min Act: -0.0000

Data Index: 954919 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.5020. Min Act: -0.0000

Data Index: 186134 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.4400. Min Act: -0.0000

Data Index: 991448 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.4764. Min Act: -0.0000

Data Index: 898823 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.3515. Min Act: -0.0000

Data Index: 92919 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.4235. Min Act: -0.0000

Data Index: 251503 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1339493 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 2.3816. Min Range: -2.3816

Max Act: 1.3818. Min Act: -0.0000

Data Index: 1176210 (C4 (Web Text))

Max Activating Token Index: 983