Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2044 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1517. Min Range: -1.1517

Max Act: 1.1517. Min Act: -0.0000

Data Index: 370105 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.1517. Min Range: -1.1517

Max Act: 1.0174. Min Act: -0.0001

Data Index: 665396 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 1.1517. Min Range: -1.1517

Max Act: 1.0185. Min Act: -0.0001

Data Index: 455653 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9560. Min Act: -0.0001

Data Index: 588765 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8228. Min Act: -0.0001

Data Index: 1257837 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8704. Min Act: -0.0001

Data Index: 1305417 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9168. Min Act: -0.0000

Data Index: 508500 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8130. Min Act: -0.0000

Data Index: 668028 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8529. Min Act: -0.0001

Data Index: 654394 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8601. Min Act: -0.0000

Data Index: 837173 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8735. Min Act: -0.0001

Data Index: 430739 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8339. Min Act: -0.0000

Data Index: 199838 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.7809. Min Act: -0.0001

Data Index: 646235 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8002. Min Act: -0.0000

Data Index: 279941 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.7973. Min Act: -0.0000

Data Index: 289461 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8221. Min Act: -0.0001

Data Index: 864578 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.7649. Min Act: -0.0001

Data Index: 790053 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.7384. Min Act: -0.0001

Data Index: 760495 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.7838. Min Act: -0.0000

Data Index: 313293 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8106. Min Act: -0.0000

Data Index: 428659 (C4 (Web Text))

Max Activating Token Index: 305