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

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

Neuron 4690 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.7463. Min Act: -0.0002

Data Index: 1400459 (Python Code)

Max Activating Token Index: 580

Text #1

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6826. Min Act: -0.0003

Data Index: 1624647 (Python Code)

Max Activating Token Index: 166

Text #2

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6889. Min Act: -0.0003

Data Index: 1519596 (Python Code)

Max Activating Token Index: 307

Text #3

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6664. Min Act: -0.0003

Data Index: 1372755 (Python Code)

Max Activating Token Index: 505

Text #4

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6471. Min Act: -0.0003

Data Index: 1458201 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6605. Min Act: -0.0002

Data Index: 1572096 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6468. Min Act: -0.0003

Data Index: 1629306 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6245. Min Act: -0.0002

Data Index: 1530692 (Python Code)

Max Activating Token Index: 330

Text #8

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6651. Min Act: -0.0003

Data Index: 1383468 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6293. Min Act: -0.0002

Data Index: 1612342 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6320. Min Act: -0.0002

Data Index: 1548661 (Python Code)

Max Activating Token Index: 625

Text #11

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6050. Min Act: -0.0003

Data Index: 1415255 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6147. Min Act: -0.0002

Data Index: 1536795 (Python Code)

Max Activating Token Index: 487

Text #13

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6169. Min Act: -0.0002

Data Index: 1595612 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5915. Min Act: -0.0002

Data Index: 1549638 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.6024. Min Act: -0.0003

Data Index: 1616904 (Python Code)

Max Activating Token Index: 129

Text #16

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5815. Min Act: -0.0003

Data Index: 1429375 (Python Code)

Max Activating Token Index: 135

Text #17

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5954. Min Act: -0.0002

Data Index: 1650075 (Python Code)

Max Activating Token Index: 120

Text #18

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5809. Min Act: -0.0002

Data Index: 1446617 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 0.7463. Min Range: -0.7463

Max Act: 0.5919. Min Act: -0.0003

Data Index: 1390915 (Python Code)

Max Activating Token Index: 485