Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1862 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1845. Min Act: -0.0001

Data Index: 1427187 (Python Code)

Max Activating Token Index: 333

Text #1

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.2523. Min Act: -0.0001

Data Index: 1386250 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1751. Min Act: -0.0001

Data Index: 1519607 (Python Code)

Max Activating Token Index: 833

Text #3

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1367. Min Act: -0.0001

Data Index: 1607932 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1043. Min Act: -0.0001

Data Index: 1505258 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0444. Min Act: -0.0001

Data Index: 1373575 (Python Code)

Max Activating Token Index: 446

Text #6

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0430. Min Act: -0.0001

Data Index: 1597724 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1171. Min Act: -0.0001

Data Index: 1533819 (Python Code)

Max Activating Token Index: 182

Text #8

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.9801. Min Act: -0.0001

Data Index: 1642340 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.9848. Min Act: -0.0001

Data Index: 1502083 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0145. Min Act: -0.0001

Data Index: 1403292 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0030. Min Act: -0.0001

Data Index: 1397698 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0044. Min Act: -0.0001

Data Index: 1577243 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.7874. Min Act: -0.0001

Data Index: 1452443 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.8547. Min Act: -0.0001

Data Index: 1405159 (Python Code)

Max Activating Token Index: 715

Text #15

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.9092. Min Act: -0.0001

Data Index: 1563266 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0181. Min Act: -0.0001

Data Index: 1483806 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.9036. Min Act: -0.0001

Data Index: 1498057 (Python Code)

Max Activating Token Index: 205

Text #18

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.9002. Min Act: -0.0001

Data Index: 1449555 (Python Code)

Max Activating Token Index: 153

Text #19

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.8918. Min Act: -0.0001

Data Index: 1614981 (Python Code)

Max Activating Token Index: 53