Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 157 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6522. Min Act: -0.0000

Data Index: 212268 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5583. Min Act: -0.0000

Data Index: 115202 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5392. Min Act: -0.0000

Data Index: 882666 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5390. Min Act: -0.0000

Data Index: 207983 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5566. Min Act: -0.0000

Data Index: 140933 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1339986 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5402. Min Act: -0.0000

Data Index: 660466 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4953. Min Act: -0.0000

Data Index: 599448 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1103626 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4434. Min Act: -0.0000

Data Index: 444379 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1072039 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1039202 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4652. Min Act: -0.0000

Data Index: 690743 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4457. Min Act: -0.0000

Data Index: 576416 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1153843 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4462. Min Act: -0.0000

Data Index: 478696 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1087432 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1153341 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4328. Min Act: -0.0000

Data Index: 437355 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4342. Min Act: -0.0000

Data Index: 853621 (C4 (Web Text))

Max Activating Token Index: 197