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

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

Neuron 2968 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.1109. Min Act: -0.0001

Data Index: 351254 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0460. Min Act: -0.0000

Data Index: 903425 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0822. Min Act: -0.0001

Data Index: 388220 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7279. Min Act: -0.0000

Data Index: 681486 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7907. Min Act: -0.0001

Data Index: 942088 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.6536. Min Act: -0.0001

Data Index: 644329 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.5817. Min Act: -0.0001

Data Index: 813145 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.5846. Min Act: -0.0001

Data Index: 812385 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.4355. Min Act: -0.0000

Data Index: 27186 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.4130. Min Act: -0.0001

Data Index: 879145 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.5019. Min Act: -0.0000

Data Index: 978106 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.4865. Min Act: -0.0000

Data Index: 66611 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.6116. Min Act: -0.0001

Data Index: 571265 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.2904. Min Act: -0.0001

Data Index: 25172 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.2877. Min Act: -0.0001

Data Index: 936489 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.3338. Min Act: -0.0000

Data Index: 89384 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.3268. Min Act: -0.0001

Data Index: 187988 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.0701. Min Act: -0.0001

Data Index: 750140 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.4194. Min Act: -0.0001

Data Index: 1195087 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.1370. Min Act: -0.0000

Data Index: 845830 (C4 (Web Text))

Max Activating Token Index: 273