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

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

Neuron 4732 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.6723. Min Act: -0.0000

Data Index: 1632270 (Python Code)

Max Activating Token Index: 337

Text #1

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3531. Min Act: -0.0000

Data Index: 1385079 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1519316 (Python Code)

Max Activating Token Index: 238

Text #3

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1541120 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3080. Min Act: -0.0001

Data Index: 1513846 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1392479 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1626859 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1562076 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1383464 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1408835 (Python Code)

Max Activating Token Index: 599

Text #10

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1655333 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1571489 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1392901 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2057. Min Act: -0.0000

Data Index: 1387420 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1476737 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1434109 (Python Code)

Max Activating Token Index: 574

Text #16

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1610501 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1424178 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1468007 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.1482. Min Act: -0.0000

Data Index: 1470428 (Python Code)

Max Activating Token Index: 446