Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3774 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1389. Min Range: -2.1389

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1612989 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.8942. Min Act: -0.0000

Data Index: 1373332 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.5654. Min Act: -0.0000

Data Index: 1637340 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6876. Min Act: -0.0000

Data Index: 1438195 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1383181 (Python Code)

Max Activating Token Index: 967

Text #5

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.5771. Min Act: -0.0000

Data Index: 1611839 (Python Code)

Max Activating Token Index: 755

Text #6

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.4045. Min Act: -0.0000

Data Index: 1648023 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1565838 (Python Code)

Max Activating Token Index: 391

Text #8

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1361278 (Python Code)

Max Activating Token Index: 382

Text #9

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1396519 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1615600 (Python Code)

Max Activating Token Index: 632

Text #11

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1451036 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1386606 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1424649 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1488470 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1536279 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.4333. Min Act: -0.0000

Data Index: 1624249 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1435395 (Python Code)

Max Activating Token Index: 290

Text #18

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1501586 (Python Code)

Max Activating Token Index: 305

Text #19

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1460663 (Python Code)

Max Activating Token Index: 816