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

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

Neuron 832 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.4068. Min Act: -0.0001

Data Index: 10043 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.4148. Min Act: -0.0001

Data Index: 1081859 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3757. Min Act: -0.0001

Data Index: 218701 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3834. Min Act: -0.0001

Data Index: 78916 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3474. Min Act: -0.0001

Data Index: 1297370 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3646. Min Act: -0.0001

Data Index: 153977 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3452. Min Act: -0.0001

Data Index: 282595 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3199. Min Act: -0.0001

Data Index: 252235 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3299. Min Act: -0.0001

Data Index: 1286684 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3189. Min Act: -0.0001

Data Index: 455128 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3117. Min Act: -0.0001

Data Index: 567925 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3026. Min Act: -0.0001

Data Index: 1028651 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1125441 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2946. Min Act: -0.0001

Data Index: 807910 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2919. Min Act: -0.0001

Data Index: 172727 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2911. Min Act: -0.0001

Data Index: 1048937 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2958. Min Act: -0.0001

Data Index: 634372 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1017745 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2833. Min Act: -0.0001

Data Index: 1296393 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2776. Min Act: -0.0001

Data Index: 960992 (C4 (Web Text))

Max Activating Token Index: 634