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

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

Neuron 2996 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0039. Min Act: -0.0003

Data Index: 330764 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0038. Min Act: -0.0003

Data Index: 528244 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1059941 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1118535 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0038. Min Act: -0.0003

Data Index: 817988 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1011906 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0036. Min Act: -0.0003

Data Index: 691946 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0036. Min Act: -0.0003

Data Index: 558862 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0034. Min Act: -0.0002

Data Index: 603641 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0034. Min Act: -0.0003

Data Index: 358571 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0034. Min Act: -0.0002

Data Index: 692092 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0033. Min Act: -0.0003

Data Index: 298551 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0031. Min Act: -0.0003

Data Index: 141802 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1187208 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1140824 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0033. Min Act: -0.0003

Data Index: 648936 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0003

Data Index: 760105 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0002

Data Index: 616606 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0030. Min Act: -0.0003

Data Index: 184100 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1343118 (C4 (Web Text))

Max Activating Token Index: 4