Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 534 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0487. Min Act: -0.0001

Data Index: 879444 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1394504 (Python Code)

Max Activating Token Index: 512

Text #2

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0475. Min Act: -0.0001

Data Index: 592379 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0462. Min Act: -0.0001

Data Index: 271054 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1630299 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1417462 (Python Code)

Max Activating Token Index: 841

Text #6

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1496552 (Python Code)

Max Activating Token Index: 986

Text #7

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1424524 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1620157 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0426. Min Act: -0.0000

Data Index: 197833 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0423. Min Act: 0.0000

Data Index: 975334 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1495256 (Python Code)

Max Activating Token Index: 1002

Text #12

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1390299 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0421. Min Act: -0.0001

Data Index: 633379 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1106193 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1015310 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0406. Min Act: -0.0001

Data Index: 972255 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1141077 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0364. Min Act: -0.0001

Data Index: 100544 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0396. Min Act: -0.0002

Data Index: 424287 (C4 (Web Text))

Max Activating Token Index: 55