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

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

Neuron 981 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: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0006

Data Index: 1212625 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0490. Min Act: -0.0006

Data Index: 17801 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0493. Min Act: -0.0006

Data Index: 18964 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1140698 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0488. Min Act: -0.0006

Data Index: 44591 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0474. Min Act: -0.0006

Data Index: 604085 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0478. Min Act: -0.0006

Data Index: 805326 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0462. Min Act: -0.0006

Data Index: 873738 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0469. Min Act: -0.0006

Data Index: 20506 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0444. Min Act: -0.0006

Data Index: 1020797 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0489. Min Act: -0.0006

Data Index: 873625 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0419. Min Act: -0.0006

Data Index: 268283 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0398. Min Act: -0.0006

Data Index: 1251838 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1302960 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0437. Min Act: -0.0006

Data Index: 712753 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0427. Min Act: -0.0006

Data Index: 192784 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0433. Min Act: -0.0006

Data Index: 64492 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0424. Min Act: -0.0006

Data Index: 175064 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0399. Min Act: -0.0006

Data Index: 65609 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1064240 (C4 (Web Text))

Max Activating Token Index: 249