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

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

Neuron 2220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.8803. Min Act: -0.0000

Data Index: 1582470 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.3321. Min Act: -0.0000

Data Index: 1584932 (Python Code)

Max Activating Token Index: 794

Text #2

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.5770. Min Act: -0.0000

Data Index: 1359868 (Python Code)

Max Activating Token Index: 195

Text #3

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.5177. Min Act: -0.0000

Data Index: 1560392 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.2514. Min Act: -0.0000

Data Index: 1449140 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.4014. Min Act: -0.0000

Data Index: 1627225 (Python Code)

Max Activating Token Index: 444

Text #6

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.0402. Min Act: -0.0000

Data Index: 1505465 (Python Code)

Max Activating Token Index: 632

Text #7

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.0460. Min Act: -0.0000

Data Index: 1402184 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.1256. Min Act: -0.0000

Data Index: 1500245 (Python Code)

Max Activating Token Index: 375

Text #9

Max Range: 4.8803. Min Range: -4.8803

Max Act: 3.9649. Min Act: -0.0000

Data Index: 1611247 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.1044. Min Act: -0.0000

Data Index: 1516438 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 4.8803. Min Range: -4.8803

Max Act: 3.7678. Min Act: -0.0000

Data Index: 1561427 (Python Code)

Max Activating Token Index: 231

Text #12

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.0432. Min Act: -0.0000

Data Index: 1400786 (Python Code)

Max Activating Token Index: 449

Text #13

Max Range: 4.8803. Min Range: -4.8803

Max Act: 3.8747. Min Act: -0.0000

Data Index: 1604911 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.2171. Min Act: -0.0000

Data Index: 1488793 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.1885. Min Act: -0.0000

Data Index: 1572114 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.1770. Min Act: -0.0000

Data Index: 1407365 (Python Code)

Max Activating Token Index: 1004

Text #17

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.0263. Min Act: -0.0000

Data Index: 1452265 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.1747. Min Act: -0.0000

Data Index: 1597710 (Python Code)

Max Activating Token Index: 401

Text #19

Max Range: 4.8803. Min Range: -4.8803

Max Act: 4.1796. Min Act: -0.0000

Data Index: 1573671 (Python Code)

Max Activating Token Index: 770