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

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

Neuron 1940 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1614903 (Python Code)

Max Activating Token Index: 804

Text #1

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1567756 (Python Code)

Max Activating Token Index: 411

Text #2

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1585434 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1650731 (Python Code)

Max Activating Token Index: 728

Text #4

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1641662 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1623167 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1532395 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1498106 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1547255 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1384026 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1527229 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1448569 (Python Code)

Max Activating Token Index: 458

Text #12

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1366539 (Python Code)

Max Activating Token Index: 256

Text #13

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1561835 (Python Code)

Max Activating Token Index: 345

Text #14

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1395121 (Python Code)

Max Activating Token Index: 291

Text #15

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1468442 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1558579 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1633194 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1401189 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1562316 (Python Code)

Max Activating Token Index: 999