Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3414 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9638. Min Act: -0.0003

Data Index: 1615613 (Python Code)

Max Activating Token Index: 626

Text #1

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0643. Min Act: -0.0003

Data Index: 1548643 (Python Code)

Max Activating Token Index: 725

Text #2

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9677. Min Act: -0.0003

Data Index: 1512361 (Python Code)

Max Activating Token Index: 292

Text #3

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0354. Min Act: -0.0003

Data Index: 1447904 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0217. Min Act: -0.0003

Data Index: 1482144 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9751. Min Act: -0.0003

Data Index: 1360957 (Python Code)

Max Activating Token Index: 799

Text #6

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9084. Min Act: -0.0003

Data Index: 1473391 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8974. Min Act: -0.0003

Data Index: 1369130 (Python Code)

Max Activating Token Index: 682

Text #8

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9503. Min Act: -0.0003

Data Index: 1428053 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8808. Min Act: -0.0003

Data Index: 1484225 (Python Code)

Max Activating Token Index: 684

Text #10

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9280. Min Act: -0.0003

Data Index: 1418996 (Python Code)

Max Activating Token Index: 694

Text #11

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9006. Min Act: -0.0003

Data Index: 1379835 (Python Code)

Max Activating Token Index: 482

Text #12

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8907. Min Act: -0.0003

Data Index: 1636170 (Python Code)

Max Activating Token Index: 326

Text #13

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8310. Min Act: -0.0003

Data Index: 1381384 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8335. Min Act: -0.0003

Data Index: 1598339 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8781. Min Act: -0.0004

Data Index: 1435173 (Python Code)

Max Activating Token Index: 650

Text #16

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8514. Min Act: -0.0003

Data Index: 1439231 (Python Code)

Max Activating Token Index: 1004

Text #17

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9283. Min Act: -0.0003

Data Index: 1449280 (Python Code)

Max Activating Token Index: 301

Text #18

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8470. Min Act: -0.0003

Data Index: 1381026 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9005. Min Act: -0.0003

Data Index: 1582113 (Python Code)

Max Activating Token Index: 650