Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4398 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.9591. Min Act: -0.0000

Data Index: 819886 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.9646. Min Act: -0.0000

Data Index: 609451 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.8630. Min Act: -0.0000

Data Index: 821448 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.8262. Min Act: -0.0000

Data Index: 641022 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.8576. Min Act: 0.0000

Data Index: 7279 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1220614 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.8158. Min Act: -0.0000

Data Index: 930354 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.8412. Min Act: 0.0001

Data Index: 1115669 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.7790. Min Act: 0.0000

Data Index: 830833 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.8524. Min Act: -0.0000

Data Index: 977793 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.7363. Min Act: 0.0000

Data Index: 210045 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.7319. Min Act: -0.0000

Data Index: 250462 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.7420. Min Act: -0.0000

Data Index: 337327 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1088941 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.7056. Min Act: -0.0000

Data Index: 867037 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.6820. Min Act: -0.0000

Data Index: 648597 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.6862. Min Act: -0.0000

Data Index: 519508 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.6777. Min Act: -0.0000

Data Index: 748052 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.7148. Min Act: -0.0000

Data Index: 463924 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.9646. Min Range: -0.9646

Max Act: 0.6517. Min Act: 0.0000

Data Index: 110181 (C4 (Web Text))

Max Activating Token Index: 271