Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1950 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1064. Min Act: -0.0003

Data Index: 1518355 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1070. Min Act: -0.0003

Data Index: 1513801 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1049. Min Act: -0.0004

Data Index: 1648224 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0979. Min Act: -0.0003

Data Index: 1627110 (Python Code)

Max Activating Token Index: 239

Text #4

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0959. Min Act: -0.0003

Data Index: 1485883 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0967. Min Act: -0.0003

Data Index: 1576563 (Python Code)

Max Activating Token Index: 372

Text #6

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1633816 (Python Code)

Max Activating Token Index: 855

Text #7

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0869. Min Act: -0.0003

Data Index: 1606856 (Python Code)

Max Activating Token Index: 510

Text #8

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1394419 (Python Code)

Max Activating Token Index: 605

Text #9

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0885. Min Act: -0.0003

Data Index: 1410325 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1391773 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1565355 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1524599 (Python Code)

Max Activating Token Index: 513

Text #13

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1485378 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0870. Min Act: -0.0003

Data Index: 1535421 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0842. Min Act: -0.0003

Data Index: 1411640 (Python Code)

Max Activating Token Index: 229

Text #16

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0897. Min Act: -0.0003

Data Index: 1531933 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0838. Min Act: -0.0003

Data Index: 1502117 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1504424 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1649599 (Python Code)

Max Activating Token Index: 302