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

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

Neuron 3539 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: 2.9411. Min Range: -2.9411

Max Act: 2.8745. Min Act: -0.0001

Data Index: 1454492 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.9411. Min Act: -0.0000

Data Index: 1378965 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.6155. Min Act: -0.0001

Data Index: 1438128 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.3990. Min Act: -0.0001

Data Index: 1400781 (Python Code)

Max Activating Token Index: 820

Text #4

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.3058. Min Act: -0.0000

Data Index: 1412801 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.3631. Min Act: -0.0000

Data Index: 1561880 (Python Code)

Max Activating Token Index: 77

Text #6

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.0801. Min Act: -0.0000

Data Index: 1374931 (Python Code)

Max Activating Token Index: 275

Text #7

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.2554. Min Act: -0.0000

Data Index: 1422565 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.2657. Min Act: -0.0000

Data Index: 1370892 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.2920. Min Act: -0.0000

Data Index: 1548914 (Python Code)

Max Activating Token Index: 190

Text #10

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.2973. Min Act: -0.0000

Data Index: 1488955 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 2.9411. Min Range: -2.9411

Max Act: 1.9118. Min Act: -0.0000

Data Index: 1558425 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.0476. Min Act: -0.0000

Data Index: 1554997 (Python Code)

Max Activating Token Index: 493

Text #13

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.1129. Min Act: -0.0000

Data Index: 1621986 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.1051. Min Act: -0.0000

Data Index: 1550612 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.2169. Min Act: -0.0000

Data Index: 1525117 (Python Code)

Max Activating Token Index: 248

Text #16

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.0941. Min Act: -0.0000

Data Index: 1400454 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.1504. Min Act: -0.0000

Data Index: 1390999 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.1339. Min Act: -0.0001

Data Index: 1469114 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 2.9411. Min Range: -2.9411

Max Act: 2.0663. Min Act: -0.0000

Data Index: 1441824 (Python Code)

Max Activating Token Index: 139