Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 913 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1395547 (Python Code)

Max Activating Token Index: 172

Text #1

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1163751 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0972. Min Act: -0.0002

Data Index: 251781 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1011. Min Act: -0.0002

Data Index: 397974 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0967. Min Act: -0.0002

Data Index: 977557 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1018. Min Act: -0.0002

Data Index: 709726 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1082. Min Act: -0.0002

Data Index: 918970 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0922. Min Act: -0.0002

Data Index: 448315 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0961. Min Act: -0.0002

Data Index: 856100 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0932. Min Act: -0.0002

Data Index: 698559 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0987. Min Act: -0.0002

Data Index: 840640 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1004849 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0893. Min Act: -0.0002

Data Index: 392375 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0977. Min Act: -0.0002

Data Index: 672930 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0938. Min Act: -0.0002

Data Index: 201139 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1000. Min Act: -0.0002

Data Index: 467700 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0955. Min Act: -0.0002

Data Index: 998936 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0847. Min Act: -0.0002

Data Index: 423026 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0981. Min Act: -0.0002

Data Index: 1015736 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1173928 (C4 (Web Text))

Max Activating Token Index: 632