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

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

Neuron 2910 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: 1.3723. Min Range: -1.3723

Max Act: 1.3289. Min Act: -0.0000

Data Index: 1548115 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1399450 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.2809. Min Act: -0.0000

Data Index: 1441317 (Python Code)

Max Activating Token Index: 243

Text #3

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1500115 (Python Code)

Max Activating Token Index: 870

Text #4

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.2432. Min Act: -0.0000

Data Index: 1536376 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.2262. Min Act: -0.0000

Data Index: 1406076 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.1872. Min Act: -0.0000

Data Index: 1507892 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1634318 (Python Code)

Max Activating Token Index: 56

Text #8

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1400334 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1559336 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1401859 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1572205 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1582142 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1465138 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1561772 (Python Code)

Max Activating Token Index: 955

Text #15

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0284. Min Act: -0.0000

Data Index: 1401582 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1566542 (Python Code)

Max Activating Token Index: 228

Text #17

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1550389 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1653841 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1497495 (Python Code)

Max Activating Token Index: 803