Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1382 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.3934. Min Act: -0.0000

Data Index: 995114 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.1820. Min Act: -0.0000

Data Index: 342161 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9863. Min Act: -0.0000

Data Index: 156801 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.2068. Min Act: -0.0000

Data Index: 829457 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.0706. Min Act: -0.0000

Data Index: 186166 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.0803. Min Act: -0.0000

Data Index: 748337 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.0030. Min Act: -0.0000

Data Index: 499018 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.1284. Min Act: -0.0000

Data Index: 195832 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.0245. Min Act: -0.0000

Data Index: 574559 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.0387. Min Act: -0.0000

Data Index: 691566 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9519. Min Act: -0.0000

Data Index: 124306 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.3934. Min Range: -1.3934

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1240536 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9984. Min Act: -0.0000

Data Index: 703621 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1191958 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1070791 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1342499 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9636. Min Act: -0.0000

Data Index: 502486 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1166904 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9039. Min Act: -0.0000

Data Index: 843722 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.3934. Min Range: -1.3934

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1223144 (C4 (Web Text))

Max Activating Token Index: 364