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

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

Neuron 3579 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.9953. Min Act: -0.0000

Data Index: 1160118 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 4.1419. Min Range: -4.1419

Max Act: 4.1419. Min Act: -0.0000

Data Index: 430643 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 4.1419. Min Range: -4.1419

Max Act: 4.0066. Min Act: -0.0000

Data Index: 404665 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.3715. Min Act: -0.0000

Data Index: 82979 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.5586. Min Act: -0.0000

Data Index: 363041 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.6865. Min Act: -0.0000

Data Index: 509422 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.3191. Min Act: -0.0000

Data Index: 249545 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.4396. Min Act: -0.0000

Data Index: 221652 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.3059. Min Act: -0.0000

Data Index: 1310847 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.2494. Min Act: -0.0000

Data Index: 147213 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.1918. Min Act: -0.0000

Data Index: 948235 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.0623. Min Act: -0.0000

Data Index: 503812 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.0314. Min Act: -0.0000

Data Index: 816116 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.3272. Min Act: -0.0000

Data Index: 447498 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.2582. Min Act: -0.0000

Data Index: 150029 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.0437. Min Act: -0.0000

Data Index: 1324304 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.4899. Min Act: -0.0000

Data Index: 1328315 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.1809. Min Act: -0.0000

Data Index: 592334 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.3092. Min Act: -0.0000

Data Index: 879137 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 4.1419. Min Range: -4.1419

Max Act: 3.1438. Min Act: -0.0000

Data Index: 732737 (C4 (Web Text))

Max Activating Token Index: 940