Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 188 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1095843 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0707. Min Act: -0.0002

Data Index: 767960 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0656. Min Act: -0.0002

Data Index: 749719 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0002

Data Index: 853061 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1279932 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0665. Min Act: -0.0002

Data Index: 553747 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0677. Min Act: -0.0002

Data Index: 507956 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0681. Min Act: -0.0002

Data Index: 294481 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0591. Min Act: -0.0002

Data Index: 430423 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1259038 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0593. Min Act: -0.0002

Data Index: 471106 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0568. Min Act: -0.0002

Data Index: 401363 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0712. Min Act: -0.0002

Data Index: 134828 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0528. Min Act: -0.0002

Data Index: 862528 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0568. Min Act: -0.0002

Data Index: 173646 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0613. Min Act: -0.0002

Data Index: 573798 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1148873 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0572. Min Act: -0.0002

Data Index: 997599 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0550. Min Act: -0.0002

Data Index: 537598 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0549. Min Act: -0.0002

Data Index: 222644 (C4 (Web Text))

Max Activating Token Index: 512