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

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

Neuron 3499 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1427727 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1436196 (Python Code)

Max Activating Token Index: 237

Text #2

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1648183 (Python Code)

Max Activating Token Index: 385

Text #3

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1476329 (Python Code)

Max Activating Token Index: 299

Text #4

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1608080 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1595767 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1378238 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1642737 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1479027 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1985. Min Act: -0.0001

Data Index: 1516108 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1593919 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1516380 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1453920 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1443302 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1468669 (Python Code)

Max Activating Token Index: 270

Text #15

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1487068 (Python Code)

Max Activating Token Index: 129

Text #16

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1433337 (Python Code)

Max Activating Token Index: 914

Text #17

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1636968 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1599088 (Python Code)

Max Activating Token Index: 623

Text #19

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1507270 (Python Code)

Max Activating Token Index: 500