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

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

Neuron 5055 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: 2.5452. Min Range: -2.5452

Max Act: 2.5452. Min Act: -0.0000

Data Index: 1529861 (Python Code)

Max Activating Token Index: 569

Text #1

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.5234. Min Act: -0.0000

Data Index: 1489901 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.4001. Min Act: -0.0000

Data Index: 1395612 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.3405. Min Act: -0.0000

Data Index: 1380826 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.0186. Min Act: -0.0000

Data Index: 1368538 (Python Code)

Max Activating Token Index: 858

Text #5

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.2212. Min Act: -0.0000

Data Index: 1426946 (Python Code)

Max Activating Token Index: 503

Text #6

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.1699. Min Act: -0.0000

Data Index: 1548040 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.2436. Min Act: -0.0000

Data Index: 1473936 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.4340. Min Act: -0.0000

Data Index: 1439849 (Python Code)

Max Activating Token Index: 181

Text #9

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.1138. Min Act: -0.0000

Data Index: 1504968 (Python Code)

Max Activating Token Index: 497

Text #10

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.1411. Min Act: -0.0000

Data Index: 1425236 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.2035. Min Act: -0.0000

Data Index: 1428604 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.0738. Min Act: -0.0000

Data Index: 1521220 (Python Code)

Max Activating Token Index: 722

Text #13

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.0707. Min Act: -0.0000

Data Index: 1457159 (Python Code)

Max Activating Token Index: 374

Text #14

Max Range: 2.5452. Min Range: -2.5452

Max Act: 1.9090. Min Act: -0.0000

Data Index: 1368435 (Python Code)

Max Activating Token Index: 635

Text #15

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.0629. Min Act: -0.0000

Data Index: 1548892 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 2.5452. Min Range: -2.5452

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1528062 (Python Code)

Max Activating Token Index: 276

Text #17

Max Range: 2.5452. Min Range: -2.5452

Max Act: 1.9365. Min Act: -0.0000

Data Index: 1438880 (Python Code)

Max Activating Token Index: 651

Text #18

Max Range: 2.5452. Min Range: -2.5452

Max Act: 1.8113. Min Act: -0.0000

Data Index: 1620783 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 2.5452. Min Range: -2.5452

Max Act: 2.0336. Min Act: -0.0000

Data Index: 1542441 (Python Code)

Max Activating Token Index: 45