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

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

Neuron 4179 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1088338 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9646. Min Act: -0.0000

Data Index: 399301 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1290349 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9666. Min Act: -0.0000

Data Index: 154061 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7996. Min Act: -0.0000

Data Index: 934323 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9236. Min Act: -0.0000

Data Index: 538533 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7932. Min Act: -0.0000

Data Index: 966341 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8058. Min Act: -0.0000

Data Index: 843868 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1125485 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1350424 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8278. Min Act: -0.0000

Data Index: 133357 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7989. Min Act: -0.0000

Data Index: 61463 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8622. Min Act: -0.0000

Data Index: 323813 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7808. Min Act: -0.0000

Data Index: 983553 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8004. Min Act: -0.0000

Data Index: 184006 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7731. Min Act: -0.0000

Data Index: 750432 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1335686 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7874. Min Act: -0.0000

Data Index: 637068 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1032421 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7842. Min Act: -0.0000

Data Index: 487681 (C4 (Web Text))

Max Activating Token Index: 468