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

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

Neuron 1298 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5206. Min Range: -2.5206

Max Act: 2.5206. Min Act: -0.0001

Data Index: 1551586 (Python Code)

Max Activating Token Index: 424

Text #1

Max Range: 2.5206. Min Range: -2.5206

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1398349 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 2.5206. Min Range: -2.5206

Max Act: 2.1037. Min Act: -0.0000

Data Index: 1382647 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.9873. Min Act: -0.0000

Data Index: 1553459 (Python Code)

Max Activating Token Index: 671

Text #4

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.7465. Min Act: -0.0000

Data Index: 1525436 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.6594. Min Act: -0.0001

Data Index: 1511576 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.6573. Min Act: -0.0001

Data Index: 1594459 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.6564. Min Act: -0.0001

Data Index: 1639756 (Python Code)

Max Activating Token Index: 311

Text #8

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1376531 (Python Code)

Max Activating Token Index: 554

Text #9

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.6763. Min Act: -0.0001

Data Index: 1520432 (Python Code)

Max Activating Token Index: 750

Text #10

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.6145. Min Act: -0.0000

Data Index: 1456181 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.6564. Min Act: -0.0001

Data Index: 1449472 (Python Code)

Max Activating Token Index: 493

Text #12

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.5963. Min Act: -0.0000

Data Index: 1523436 (Python Code)

Max Activating Token Index: 325

Text #13

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.5844. Min Act: -0.0000

Data Index: 1530834 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.6042. Min Act: -0.0000

Data Index: 1585844 (Python Code)

Max Activating Token Index: 565

Text #15

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1532387 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.5932. Min Act: -0.0000

Data Index: 1431887 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.4292. Min Act: -0.0000

Data Index: 1594711 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1569865 (Python Code)

Max Activating Token Index: 523

Text #19

Max Range: 2.5206. Min Range: -2.5206

Max Act: 1.5746. Min Act: -0.0000

Data Index: 1427620 (Python Code)

Max Activating Token Index: 942