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

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

Neuron 238 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1527. Min Range: -1.1527

Max Act: 1.1527. Min Act: -0.0001

Data Index: 1466907 (Python Code)

Max Activating Token Index: 715

Text #1

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9519. Min Act: -0.0001

Data Index: 1564626 (Python Code)

Max Activating Token Index: 487

Text #2

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.8399. Min Act: -0.0001

Data Index: 1581268 (Python Code)

Max Activating Token Index: 372

Text #3

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.8185. Min Act: -0.0001

Data Index: 1517148 (Python Code)

Max Activating Token Index: 573

Text #4

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9013. Min Act: -0.0001

Data Index: 1626752 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.8660. Min Act: -0.0001

Data Index: 1519235 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.8647. Min Act: -0.0001

Data Index: 1527087 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.9162. Min Act: -0.0001

Data Index: 1417434 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1622403 (Python Code)

Max Activating Token Index: 909

Text #9

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.8556. Min Act: -0.0001

Data Index: 1385229 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.8133. Min Act: -0.0001

Data Index: 1426874 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.7580. Min Act: -0.0001

Data Index: 1557762 (Python Code)

Max Activating Token Index: 1000

Text #12

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.8538. Min Act: -0.0001

Data Index: 1637115 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.8401. Min Act: -0.0001

Data Index: 1394404 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.7432. Min Act: -0.0001

Data Index: 1542999 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.7450. Min Act: -0.0001

Data Index: 1496461 (Python Code)

Max Activating Token Index: 520

Text #16

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.7544. Min Act: -0.0001

Data Index: 1497978 (Python Code)

Max Activating Token Index: 856

Text #17

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.7472. Min Act: -0.0001

Data Index: 1464836 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1587529 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 1.1527. Min Range: -1.1527

Max Act: 0.7863. Min Act: -0.0001

Data Index: 1560829 (Python Code)

Max Activating Token Index: 398