Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1855 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1578835 (Python Code)

Max Activating Token Index: 630

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0004

Data Index: 1412899 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0004

Data Index: 1531192 (Python Code)

Max Activating Token Index: 82

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1489117 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0003

Data Index: 894975 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1576951 (Python Code)

Max Activating Token Index: 332

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1370757 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1388400 (Python Code)

Max Activating Token Index: 693

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0004

Data Index: 1525403 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1371943 (Python Code)

Max Activating Token Index: 44

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1514754 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1613371 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0004

Data Index: 1493538 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1567508 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1367911 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1483721 (Python Code)

Max Activating Token Index: 557

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1587989 (Python Code)

Max Activating Token Index: 599

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1492506 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1582527 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1467464 (Python Code)

Max Activating Token Index: 8