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

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

Neuron 3884 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.8887. Min Act: 0.0001

Data Index: 1640520 (Python Code)

Max Activating Token Index: 729

Text #1

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1636900 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1521325 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7537. Min Act: 0.0000

Data Index: 1557395 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1557456 (Python Code)

Max Activating Token Index: 839

Text #5

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1562397 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7336. Min Act: 0.0000

Data Index: 1424038 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7326. Min Act: 0.0001

Data Index: 1393387 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1572424 (Python Code)

Max Activating Token Index: 831

Text #9

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1415932 (Python Code)

Max Activating Token Index: 716

Text #10

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1369291 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1577648 (Python Code)

Max Activating Token Index: 173

Text #12

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6220. Min Act: 0.0000

Data Index: 1565195 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1558114 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1541317 (Python Code)

Max Activating Token Index: 652

Text #15

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1377643 (Python Code)

Max Activating Token Index: 957

Text #16

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6208. Min Act: 0.0000

Data Index: 1553388 (Python Code)

Max Activating Token Index: 634

Text #17

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1442731 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6706. Min Act: 0.0000

Data Index: 1531992 (Python Code)

Max Activating Token Index: 313

Text #19

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6476. Min Act: 0.0000

Data Index: 1464996 (Python Code)

Max Activating Token Index: 65