Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 993 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.3823. Min Act: -0.0000

Data Index: 1585388 (Python Code)

Max Activating Token Index: 565

Text #1

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.3616. Min Act: -0.0000

Data Index: 1467172 (Python Code)

Max Activating Token Index: 648

Text #2

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1555829 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1409142 (Python Code)

Max Activating Token Index: 117

Text #4

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1360256 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1506360 (Python Code)

Max Activating Token Index: 365

Text #6

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1480868 (Python Code)

Max Activating Token Index: 582

Text #7

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1630562 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1468483 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1620984 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1544566 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1366894 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0371. Min Act: -0.0000

Data Index: 1384766 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1547981 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1648727 (Python Code)

Max Activating Token Index: 864

Text #15

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1614400 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 1.3823. Min Range: -1.3823

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1497251 (Python Code)

Max Activating Token Index: 238

Text #17

Max Range: 1.3823. Min Range: -1.3823

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1634569 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 1.3823. Min Range: -1.3823

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1643359 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 1.3823. Min Range: -1.3823

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1397644 (Python Code)

Max Activating Token Index: 673