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

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

Neuron 1966 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: 2.4044. Min Range: -2.4044

Max Act: 2.4044. Min Act: -0.0000

Data Index: 529350 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.4044. Min Range: -2.4044

Max Act: 2.2991. Min Act: -0.0000

Data Index: 617398 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 2.4044. Min Range: -2.4044

Max Act: 2.1076. Min Act: -0.0000

Data Index: 981675 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.9688. Min Act: -0.0000

Data Index: 363813 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 2.4044. Min Range: -2.4044

Max Act: 2.0350. Min Act: -0.0000

Data Index: 401799 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.9783. Min Act: -0.0001

Data Index: 1309270 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.9363. Min Act: -0.0000

Data Index: 1191222 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.8978. Min Act: -0.0000

Data Index: 115133 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.7999. Min Act: -0.0001

Data Index: 420325 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.7627. Min Act: -0.0000

Data Index: 934717 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.7787. Min Act: -0.0000

Data Index: 696838 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1341606 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1011279 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.7479. Min Act: -0.0000

Data Index: 97782 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.8321. Min Act: -0.0001

Data Index: 862536 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.8506. Min Act: -0.0000

Data Index: 1293272 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.7997. Min Act: -0.0000

Data Index: 1325668 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.6794. Min Act: -0.0000

Data Index: 543906 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.5800. Min Act: -0.0000

Data Index: 1328651 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 2.4044. Min Range: -2.4044

Max Act: 1.8370. Min Act: -0.0000

Data Index: 877144 (C4 (Web Text))

Max Activating Token Index: 867