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

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

Neuron 227 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0006

Data Index: 720805 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0713. Min Act: -0.0006

Data Index: 537965 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0691. Min Act: -0.0006

Data Index: 853938 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0703. Min Act: -0.0006

Data Index: 751094 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0694. Min Act: -0.0006

Data Index: 481913 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0636. Min Act: -0.0006

Data Index: 83366 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0607. Min Act: -0.0006

Data Index: 524161 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0556. Min Act: -0.0006

Data Index: 728116 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0586. Min Act: -0.0006

Data Index: 853126 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0558. Min Act: -0.0006

Data Index: 458506 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0530. Min Act: -0.0006

Data Index: 983225 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0547. Min Act: -0.0006

Data Index: 484966 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0474. Min Act: -0.0006

Data Index: 463824 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0523. Min Act: -0.0006

Data Index: 1162136 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0501. Min Act: -0.0006

Data Index: 199111 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0534. Min Act: -0.0006

Data Index: 111994 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0524. Min Act: -0.0006

Data Index: 25828 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0471. Min Act: -0.0006

Data Index: 534602 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0494. Min Act: -0.0006

Data Index: 1201294 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0484. Min Act: -0.0006

Data Index: 776925 (C4 (Web Text))

Max Activating Token Index: 69