Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 685 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1202. Min Act: -0.0003

Data Index: 1424828 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1054. Min Act: -0.0003

Data Index: 1504833 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1017. Min Act: -0.0003

Data Index: 1384210 (Python Code)

Max Activating Token Index: 572

Text #3

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1001. Min Act: -0.0003

Data Index: 1616788 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0958. Min Act: -0.0003

Data Index: 1572303 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0974. Min Act: -0.0003

Data Index: 1562049 (Python Code)

Max Activating Token Index: 738

Text #6

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0894. Min Act: -0.0003

Data Index: 1443588 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0890. Min Act: -0.0003

Data Index: 1391675 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0924. Min Act: -0.0003

Data Index: 1419651 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0921. Min Act: -0.0003

Data Index: 1410238 (Python Code)

Max Activating Token Index: 183

Text #10

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1005. Min Act: -0.0003

Data Index: 1633927 (Python Code)

Max Activating Token Index: 729

Text #11

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0912. Min Act: -0.0003

Data Index: 1481100 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1529774 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0857. Min Act: -0.0003

Data Index: 1404956 (Python Code)

Max Activating Token Index: 441

Text #14

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1447806 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1545919 (Python Code)

Max Activating Token Index: 579

Text #16

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0895. Min Act: -0.0003

Data Index: 1571669 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0856. Min Act: -0.0003

Data Index: 1513988 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0870. Min Act: -0.0003

Data Index: 1611226 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0883. Min Act: -0.0003

Data Index: 1580150 (Python Code)

Max Activating Token Index: 575