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

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

Neuron 842 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4214. Min Act: -0.0003

Data Index: 5251 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4103. Min Act: -0.0003

Data Index: 73661 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4089. Min Act: -0.0003

Data Index: 254796 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4180. Min Act: -0.0003

Data Index: 821210 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3958. Min Act: -0.0003

Data Index: 1149780 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3936. Min Act: -0.0003

Data Index: 776709 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3781. Min Act: -0.0003

Data Index: 1275088 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3887. Min Act: -0.0003

Data Index: 408444 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4013. Min Act: -0.0003

Data Index: 1289475 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3805. Min Act: -0.0003

Data Index: 1230272 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3641. Min Act: -0.0003

Data Index: 1274521 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3727. Min Act: -0.0003

Data Index: 625070 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4087. Min Act: -0.0003

Data Index: 1220119 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3719. Min Act: -0.0003

Data Index: 931806 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3753. Min Act: -0.0003

Data Index: 405481 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3725. Min Act: -0.0003

Data Index: 141165 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3680. Min Act: -0.0003

Data Index: 1342697 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3620. Min Act: -0.0003

Data Index: 1114777 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3613. Min Act: -0.0003

Data Index: 758230 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3582. Min Act: -0.0003

Data Index: 615518 (C4 (Web Text))

Max Activating Token Index: 600