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

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

Neuron 2894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4699. Min Range: -2.4699

Max Act: 2.4699. Min Act: -0.0001

Data Index: 728047 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.8810. Min Act: -0.0000

Data Index: 891313 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.8923. Min Act: -0.0000

Data Index: 100492 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.8738. Min Act: -0.0000

Data Index: 461433 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.7644. Min Act: -0.0000

Data Index: 1155830 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.7792. Min Act: -0.0000

Data Index: 782301 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.7537. Min Act: -0.0000

Data Index: 1206467 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.5832. Min Act: -0.0000

Data Index: 785851 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.5091. Min Act: -0.0001

Data Index: 250895 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1110669 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.4306. Min Act: -0.0000

Data Index: 811696 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.5722. Min Act: -0.0000

Data Index: 329382 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.3191. Min Act: -0.0000

Data Index: 309039 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1270751 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1350866 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1181628 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.4363. Min Act: -0.0000

Data Index: 346434 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.3791. Min Act: -0.0001

Data Index: 1171627 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.3954. Min Act: -0.0000

Data Index: 1091343 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 2.4699. Min Range: -2.4699

Max Act: 1.3475. Min Act: -0.0000

Data Index: 1085144 (C4 (Web Text))

Max Activating Token Index: 314