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

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

Neuron 687 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0361. Min Range: -1.0361

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1536283 (Python Code)

Max Activating Token Index: 396

Text #1

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1510104 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1361074 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1572270 (Python Code)

Max Activating Token Index: 408

Text #4

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1654278 (Python Code)

Max Activating Token Index: 303

Text #5

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1489573 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1435672 (Python Code)

Max Activating Token Index: 888

Text #7

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1496495 (Python Code)

Max Activating Token Index: 815

Text #8

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1629774 (Python Code)

Max Activating Token Index: 239

Text #9

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1597360 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1371832 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1464617 (Python Code)

Max Activating Token Index: 580

Text #12

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1588623 (Python Code)

Max Activating Token Index: 841

Text #13

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1427153 (Python Code)

Max Activating Token Index: 821

Text #14

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1459505 (Python Code)

Max Activating Token Index: 175

Text #15

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1589327 (Python Code)

Max Activating Token Index: 581

Text #16

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1566373 (Python Code)

Max Activating Token Index: 502

Text #17

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1380360 (Python Code)

Max Activating Token Index: 517

Text #18

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1644487 (Python Code)

Max Activating Token Index: 610

Text #19

Max Range: 1.0361. Min Range: -1.0361

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1548581 (Python Code)

Max Activating Token Index: 786