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

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

Neuron 3420 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0256. Min Range: -1.0256

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1472580 (Python Code)

Max Activating Token Index: 982

Text #1

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1491405 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1532962 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1462808 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1386233 (Python Code)

Max Activating Token Index: 763

Text #5

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1540098 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1496015 (Python Code)

Max Activating Token Index: 470

Text #7

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1427312 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1498563 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1572148 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1570431 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1410226 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1361717 (Python Code)

Max Activating Token Index: 398

Text #13

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1652657 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1370135 (Python Code)

Max Activating Token Index: 996

Text #15

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1468098 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1013654 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1566358 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1361423 (Python Code)

Max Activating Token Index: 212

Text #19

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1452435 (Python Code)

Max Activating Token Index: 758