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

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

Neuron 3280 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1139. Min Act: -0.0001

Data Index: 948335 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1091. Min Act: -0.0002

Data Index: 387512 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1052. Min Act: -0.0002

Data Index: 15616 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0985. Min Act: -0.0002

Data Index: 838622 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0955. Min Act: -0.0001

Data Index: 901523 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1034. Min Act: -0.0002

Data Index: 24437 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0959. Min Act: -0.0002

Data Index: 965920 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1036. Min Act: -0.0002

Data Index: 449801 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1093076 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0943. Min Act: -0.0002

Data Index: 853726 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0835. Min Act: -0.0002

Data Index: 742260 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1122977 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0884. Min Act: -0.0002

Data Index: 201025 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0885. Min Act: -0.0002

Data Index: 874427 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1085260 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0925. Min Act: -0.0002

Data Index: 809168 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.1011. Min Act: -0.0002

Data Index: 76370 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0906. Min Act: -0.0002

Data Index: 951910 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0903. Min Act: -0.0002

Data Index: 971 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.1139. Min Range: -0.1139

Max Act: 0.0906. Min Act: -0.0002

Data Index: 258630 (C4 (Web Text))

Max Activating Token Index: 111