Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1002 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0559. Min Act: -0.0005

Data Index: 292160 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0553. Min Act: -0.0004

Data Index: 904138 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0568. Min Act: -0.0005

Data Index: 1138027 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0528. Min Act: -0.0005

Data Index: 433935 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0533. Min Act: -0.0005

Data Index: 314898 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0516. Min Act: -0.0005

Data Index: 636638 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0524. Min Act: -0.0005

Data Index: 476963 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0516. Min Act: -0.0005

Data Index: 1089912 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0504. Min Act: -0.0005

Data Index: 790629 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0536. Min Act: -0.0005

Data Index: 334203 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0509. Min Act: -0.0005

Data Index: 106810 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0503. Min Act: -0.0005

Data Index: 345220 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0499. Min Act: -0.0005

Data Index: 567767 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0483. Min Act: -0.0005

Data Index: 1304983 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0484. Min Act: -0.0005

Data Index: 253322 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0454. Min Act: -0.0005

Data Index: 424186 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0495. Min Act: -0.0005

Data Index: 1045695 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0498. Min Act: -0.0005

Data Index: 1171100 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0494. Min Act: -0.0005

Data Index: 1223014 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0493. Min Act: -0.0005

Data Index: 920285 (C4 (Web Text))

Max Activating Token Index: 247