Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3838 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.5562. Min Range: -6.5562

Max Act: 6.5562. Min Act: -0.0000

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 6.5562. Min Range: -6.5562

Max Act: 6.1538. Min Act: -0.0001

Data Index: 555238 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 6.5562. Min Range: -6.5562

Max Act: 5.6003. Min Act: -0.0001

Data Index: 552373 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 6.5562. Min Range: -6.5562

Max Act: 5.3999. Min Act: -0.0000

Data Index: 383404 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 6.5562. Min Range: -6.5562

Max Act: 5.4029. Min Act: -0.0000

Data Index: 378907 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 6.5562. Min Range: -6.5562

Max Act: 5.1977. Min Act: -0.0000

Data Index: 601683 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 6.5562. Min Range: -6.5562

Max Act: 5.3449. Min Act: -0.0000

Data Index: 1180710 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 6.5562. Min Range: -6.5562

Max Act: 5.0786. Min Act: -0.0000

Data Index: 426573 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.6543. Min Act: -0.0001

Data Index: 121745 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.5942. Min Act: -0.0000

Data Index: 956443 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.5530. Min Act: -0.0001

Data Index: 129924 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.5402. Min Act: -0.0000

Data Index: 893885 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.3766. Min Act: -0.0001

Data Index: 149482 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.1070. Min Act: -0.0001

Data Index: 1012350 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.0265. Min Act: -0.0000

Data Index: 883267 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.0141. Min Act: -0.0001

Data Index: 552920 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 6.5562. Min Range: -6.5562

Max Act: 3.7963. Min Act: -0.0001

Data Index: 750586 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 6.5562. Min Range: -6.5562

Max Act: 3.7414. Min Act: -0.0000

Data Index: 33775 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 6.5562. Min Range: -6.5562

Max Act: 4.2494. Min Act: -0.0001

Data Index: 801099 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 6.5562. Min Range: -6.5562

Max Act: 3.8801. Min Act: -0.0000

Data Index: 1160453 (C4 (Web Text))

Max Activating Token Index: 367