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

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

Neuron 2655 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1542168 (Python Code)

Max Activating Token Index: 459

Text #1

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2636. Min Act: -0.0000

Data Index: 1473205 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1628545 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1389363 (Python Code)

Max Activating Token Index: 736

Text #4

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1532537 (Python Code)

Max Activating Token Index: 759

Text #5

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1580722 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1609346 (Python Code)

Max Activating Token Index: 763

Text #7

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9993. Min Act: 0.0002

Data Index: 1447206 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1534214 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1473834 (Python Code)

Max Activating Token Index: 818

Text #10

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9283. Min Act: 0.0000

Data Index: 1481015 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9463. Min Act: 0.0001

Data Index: 1502040 (Python Code)

Max Activating Token Index: 156

Text #12

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.8885. Min Act: 0.0000

Data Index: 1419178 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1417970 (Python Code)

Max Activating Token Index: 998

Text #14

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1580471 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1641876 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1619385 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1601896 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1573897 (Python Code)

Max Activating Token Index: 375

Text #19

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1436984 (Python Code)

Max Activating Token Index: 282