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

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

Neuron 2764 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: 2.3497. Min Range: -2.3497

Max Act: 2.3497. Min Act: -0.0000

Data Index: 1364210 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 2.3497. Min Range: -2.3497

Max Act: 2.0043. Min Act: -0.0000

Data Index: 1413348 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.8430. Min Act: -0.0000

Data Index: 1606310 (Python Code)

Max Activating Token Index: 126

Text #3

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.7171. Min Act: -0.0000

Data Index: 1597425 (Python Code)

Max Activating Token Index: 932

Text #4

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.8102. Min Act: -0.0000

Data Index: 1545946 (Python Code)

Max Activating Token Index: 386

Text #5

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.7837. Min Act: -0.0000

Data Index: 1369413 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1629246 (Python Code)

Max Activating Token Index: 568

Text #7

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.6280. Min Act: -0.0000

Data Index: 1650681 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.6302. Min Act: -0.0000

Data Index: 1592347 (Python Code)

Max Activating Token Index: 301

Text #9

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.6702. Min Act: 0.0000

Data Index: 1516120 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.6688. Min Act: 0.0000

Data Index: 1553305 (Python Code)

Max Activating Token Index: 611

Text #11

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1618121 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1591056 (Python Code)

Max Activating Token Index: 822

Text #13

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.6830. Min Act: -0.0000

Data Index: 1564649 (Python Code)

Max Activating Token Index: 153

Text #14

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1470827 (Python Code)

Max Activating Token Index: 485

Text #15

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.7745. Min Act: -0.0000

Data Index: 1433583 (Python Code)

Max Activating Token Index: 748

Text #16

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.8578. Min Act: -0.0000

Data Index: 1519072 (Python Code)

Max Activating Token Index: 737

Text #17

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.5198. Min Act: -0.0000

Data Index: 1411192 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1600057 (Python Code)

Max Activating Token Index: 198

Text #19

Max Range: 2.3497. Min Range: -2.3497

Max Act: 1.6146. Min Act: -0.0000

Data Index: 1418233 (Python Code)

Max Activating Token Index: 456