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

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

Neuron 1714 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: 1.3721. Min Range: -1.3721

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1646705 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1624402 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.1879. Min Act: -0.0000

Data Index: 1477897 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1490107 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.0042. Min Act: -0.0001

Data Index: 1394274 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9790. Min Act: -0.0001

Data Index: 1555597 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9584. Min Act: -0.0001

Data Index: 1381918 (Python Code)

Max Activating Token Index: 759

Text #7

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1421340 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1475734 (Python Code)

Max Activating Token Index: 776

Text #9

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9249. Min Act: -0.0001

Data Index: 1474365 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1587631 (Python Code)

Max Activating Token Index: 215

Text #11

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.8927. Min Act: -0.0001

Data Index: 1523054 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.8201. Min Act: -0.0001

Data Index: 1432616 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.8626. Min Act: -0.0001

Data Index: 1625565 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1648700 (Python Code)

Max Activating Token Index: 594

Text #15

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.8828. Min Act: -0.0001

Data Index: 1493118 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1378894 (Python Code)

Max Activating Token Index: 915

Text #17

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1540749 (Python Code)

Max Activating Token Index: 893

Text #18

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9052. Min Act: -0.0000

Data Index: 1538532 (Python Code)

Max Activating Token Index: 440

Text #19

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.8798. Min Act: -0.0001

Data Index: 1579900 (Python Code)

Max Activating Token Index: 502