Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2167 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5269. Min Act: -0.0001

Data Index: 1560977 (Python Code)

Max Activating Token Index: 790

Text #1

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4593. Min Act: -0.0001

Data Index: 1434803 (Python Code)

Max Activating Token Index: 295

Text #2

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4565. Min Act: -0.0001

Data Index: 1444156 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1382895 (Python Code)

Max Activating Token Index: 254

Text #4

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4169. Min Act: -0.0001

Data Index: 1597137 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4092. Min Act: -0.0001

Data Index: 1531429 (Python Code)

Max Activating Token Index: 779

Text #6

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1469954 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4290. Min Act: -0.0001

Data Index: 1410490 (Python Code)

Max Activating Token Index: 819

Text #8

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1379364 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4417. Min Act: -0.0001

Data Index: 1480005 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3727. Min Act: -0.0001

Data Index: 1410370 (Python Code)

Max Activating Token Index: 609

Text #11

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3893. Min Act: -0.0001

Data Index: 1647851 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3704. Min Act: -0.0001

Data Index: 1455387 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1511106 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3416. Min Act: -0.0001

Data Index: 1451137 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3562. Min Act: -0.0001

Data Index: 1419846 (Python Code)

Max Activating Token Index: 954

Text #16

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3682. Min Act: -0.0001

Data Index: 1589643 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3801. Min Act: -0.0001

Data Index: 1372011 (Python Code)

Max Activating Token Index: 774

Text #18

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3788. Min Act: -0.0001

Data Index: 1592905 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3607. Min Act: -0.0001

Data Index: 1420250 (Python Code)

Max Activating Token Index: 208