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

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

Neuron 537 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5972. Min Act: -0.0000

Data Index: 483848 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1237651 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1270393 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1313533 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5650. Min Act: -0.0000

Data Index: 32431 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1065553 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5404. Min Act: -0.0000

Data Index: 65116 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1099338 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5455. Min Act: -0.0000

Data Index: 543245 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5149. Min Act: -0.0000

Data Index: 346755 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1567641 (Python Code)

Max Activating Token Index: 139

Text #11

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5045. Min Act: -0.0000

Data Index: 388156 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4916. Min Act: -0.0000

Data Index: 669951 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4655. Min Act: -0.0000

Data Index: 801335 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4666. Min Act: -0.0000

Data Index: 769707 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1329647 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4448. Min Act: -0.0000

Data Index: 838171 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4235. Min Act: -0.0000

Data Index: 118985 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4699. Min Act: -0.0000

Data Index: 692773 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4705. Min Act: -0.0000

Data Index: 437901 (C4 (Web Text))

Max Activating Token Index: 14