Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2685 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1181774 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.4013. Min Act: 0.0000

Data Index: 1223416 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1059194 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3756. Min Act: -0.0000

Data Index: 800564 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3303. Min Act: -0.0000

Data Index: 261893 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3274. Min Act: -0.0000

Data Index: 51516 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1326673 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3077. Min Act: 0.0000

Data Index: 34161 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1091930 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2864. Min Act: -0.0001

Data Index: 1208719 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3107. Min Act: -0.0000

Data Index: 386163 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3069. Min Act: -0.0000

Data Index: 626265 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1356265 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2937. Min Act: -0.0000

Data Index: 124995 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2935. Min Act: -0.0000

Data Index: 386446 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2920. Min Act: -0.0000

Data Index: 763345 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2753. Min Act: -0.0000

Data Index: 562951 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2766. Min Act: 0.0000

Data Index: 672998 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2650. Min Act: -0.0001

Data Index: 741783 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.2749. Min Act: -0.0000

Data Index: 434936 (C4 (Web Text))

Max Activating Token Index: 38