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

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

Neuron 2705 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: 1.6206. Min Range: -1.6206

Max Act: 1.6206. Min Act: -0.0000

Data Index: 290601 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.5289. Min Act: -0.0000

Data Index: 400292 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.4211. Min Act: -0.0000

Data Index: 1329503 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.4421. Min Act: -0.0000

Data Index: 444442 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.3693. Min Act: -0.0000

Data Index: 450354 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.3887. Min Act: -0.0001

Data Index: 204677 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.2632. Min Act: -0.0000

Data Index: 78831 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.2197. Min Act: -0.0001

Data Index: 1015260 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.2000. Min Act: -0.0000

Data Index: 549723 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1196683 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1822. Min Act: -0.0000

Data Index: 52092 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1840. Min Act: -0.0000

Data Index: 920504 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1073. Min Act: -0.0000

Data Index: 378037 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1347. Min Act: -0.0000

Data Index: 666375 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1292690 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1093. Min Act: -0.0000

Data Index: 213558 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1782. Min Act: -0.0000

Data Index: 401715 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1090760 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0824. Min Act: -0.0000

Data Index: 299787 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 1.6206. Min Range: -1.6206

Max Act: 1.0754. Min Act: -0.0000

Data Index: 56625 (C4 (Web Text))

Max Activating Token Index: 167