Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 494 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3694. Min Act: -0.0005

Data Index: 1159891 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3213. Min Act: -0.0005

Data Index: 1205023 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3212. Min Act: -0.0005

Data Index: 995951 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3255. Min Act: -0.0005

Data Index: 943061 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3143. Min Act: -0.0005

Data Index: 358113 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3143. Min Act: -0.0005

Data Index: 552350 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3006. Min Act: -0.0005

Data Index: 1290091 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3225. Min Act: -0.0005

Data Index: 996752 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2968. Min Act: -0.0005

Data Index: 319177 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2955. Min Act: -0.0005

Data Index: 732880 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2930. Min Act: -0.0005

Data Index: 1317475 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2847. Min Act: -0.0005

Data Index: 816633 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2954. Min Act: -0.0005

Data Index: 269161 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2691. Min Act: -0.0005

Data Index: 24587 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2777. Min Act: -0.0005

Data Index: 156791 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2475. Min Act: -0.0005

Data Index: 280184 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2668. Min Act: -0.0005

Data Index: 1002973 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2654. Min Act: -0.0005

Data Index: 1311746 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2565. Min Act: -0.0005

Data Index: 564244 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2632. Min Act: -0.0005

Data Index: 593701 (C4 (Web Text))

Max Activating Token Index: 126