Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 690 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0873. Min Act: -0.0006

Data Index: 113124 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0606. Min Act: -0.0006

Data Index: 461720 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0647. Min Act: -0.0006

Data Index: 814810 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0552. Min Act: -0.0006

Data Index: 417774 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0527. Min Act: -0.0006

Data Index: 1106161 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0509. Min Act: -0.0006

Data Index: 855743 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0494. Min Act: -0.0006

Data Index: 262000 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0512. Min Act: -0.0006

Data Index: 1077266 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0491. Min Act: -0.0006

Data Index: 1245899 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0511. Min Act: -0.0006

Data Index: 195546 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0509. Min Act: -0.0006

Data Index: 1338950 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0497. Min Act: -0.0006

Data Index: 903956 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0481. Min Act: -0.0006

Data Index: 670457 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0500. Min Act: -0.0006

Data Index: 1108046 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0489. Min Act: -0.0006

Data Index: 821389 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0489. Min Act: -0.0005

Data Index: 607287 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0461. Min Act: -0.0006

Data Index: 1022341 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0488. Min Act: -0.0006

Data Index: 1087394 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0467. Min Act: -0.0006

Data Index: 579003 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0466. Min Act: -0.0006

Data Index: 1043274 (C4 (Web Text))

Max Activating Token Index: 237