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

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

Neuron 708 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: 1.0337. Min Range: -1.0337

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8783. Min Act: -0.0000

Data Index: 536084 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9285. Min Act: -0.0000

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8868. Min Act: -0.0000

Data Index: 344158 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1144836 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7986. Min Act: -0.0000

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7802. Min Act: -0.0000

Data Index: 235090 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7530. Min Act: -0.0000

Data Index: 919051 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1228040 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1198538 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.5927. Min Act: -0.0000

Data Index: 633450 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.6047. Min Act: -0.0000

Data Index: 803648 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.4776. Min Act: -0.0000

Data Index: 651974 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1030190 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.4554. Min Act: -0.0000

Data Index: 102594 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.4845. Min Act: -0.0000

Data Index: 467016 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.5068. Min Act: -0.0000

Data Index: 504281 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1015393 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.4398. Min Act: -0.0000

Data Index: 867829 (C4 (Web Text))

Max Activating Token Index: 693