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

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

Neuron 1881 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0000

Data Index: 173097 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0609. Min Act: 0.0000

Data Index: 329675 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0588. Min Act: -0.0000

Data Index: 151522 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1008230 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1590581 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0503. Min Act: -0.0000

Data Index: 249390 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1025640 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0509. Min Act: -0.0000

Data Index: 820002 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0487. Min Act: 0.0000

Data Index: 1088391 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0470. Min Act: 0.0000

Data Index: 325516 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0495. Min Act: -0.0000

Data Index: 928505 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0458. Min Act: 0.0000

Data Index: 1110071 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0451. Min Act: -0.0000

Data Index: 390241 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0432. Min Act: -0.0000

Data Index: 615210 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0444. Min Act: -0.0000

Data Index: 1098297 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0414. Min Act: -0.0000

Data Index: 694915 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0459. Min Act: 0.0000

Data Index: 867800 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0423. Min Act: -0.0000

Data Index: 428857 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0457. Min Act: 0.0000

Data Index: 1234481 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0459. Min Act: -0.0000

Data Index: 279463 (C4 (Web Text))

Max Activating Token Index: 161