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

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

Neuron 2190 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1462954 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1198776 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5962. Min Act: -0.0000

Data Index: 675044 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5673. Min Act: -0.0000

Data Index: 506471 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.6067. Min Act: -0.0000

Data Index: 457418 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5469. Min Act: -0.0000

Data Index: 379997 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5102. Min Act: -0.0000

Data Index: 472942 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1155537 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4987. Min Act: -0.0000

Data Index: 142595 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4969. Min Act: -0.0000

Data Index: 433305 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1080648 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4966. Min Act: -0.0000

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5178. Min Act: -0.0000

Data Index: 539580 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5107. Min Act: -0.0000

Data Index: 645082 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1141193 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4934. Min Act: -0.0000

Data Index: 400223 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1163343 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4851. Min Act: -0.0000

Data Index: 51848 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1325956 (C4 (Web Text))

Max Activating Token Index: 917