Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1355 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4798. Min Act: -0.0001

Data Index: 1557476 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1508749 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4045. Min Act: -0.0001

Data Index: 1593237 (Python Code)

Max Activating Token Index: 297

Text #3

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1443970 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4075. Min Act: -0.0001

Data Index: 1528226 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1381877 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1466351 (Python Code)

Max Activating Token Index: 214

Text #7

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3936. Min Act: -0.0001

Data Index: 1634283 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3843. Min Act: -0.0001

Data Index: 1648148 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4025. Min Act: -0.0001

Data Index: 1432134 (Python Code)

Max Activating Token Index: 997

Text #10

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3890. Min Act: -0.0001

Data Index: 1407623 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3486. Min Act: -0.0001

Data Index: 1390937 (Python Code)

Max Activating Token Index: 704

Text #12

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1602947 (Python Code)

Max Activating Token Index: 665

Text #13

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3601. Min Act: -0.0001

Data Index: 1477504 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1360131 (Python Code)

Max Activating Token Index: 702

Text #15

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1639527 (Python Code)

Max Activating Token Index: 819

Text #16

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3634. Min Act: 0.0000

Data Index: 1504594 (Python Code)

Max Activating Token Index: 1014

Text #17

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3473. Min Act: -0.0001

Data Index: 1591210 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3201. Min Act: -0.0001

Data Index: 855664 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1590451 (Python Code)

Max Activating Token Index: 338