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

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

Neuron 3604 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: 0.5295. Min Range: -0.5295

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1420110 (Python Code)

Max Activating Token Index: 800

Text #1

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1543205 (Python Code)

Max Activating Token Index: 804

Text #2

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1509354 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1638130 (Python Code)

Max Activating Token Index: 910

Text #4

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1456064 (Python Code)

Max Activating Token Index: 657

Text #5

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1559958 (Python Code)

Max Activating Token Index: 662

Text #6

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1628332 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1422989 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1546805 (Python Code)

Max Activating Token Index: 269

Text #9

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1360238 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1456051 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1407546 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1607841 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1544735 (Python Code)

Max Activating Token Index: 1017

Text #14

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1618456 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1573561 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1489992 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1480910 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1573557 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1608525 (Python Code)

Max Activating Token Index: 585