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

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

Neuron 3248 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1207493 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5589. Min Act: -0.0001

Data Index: 954842 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5376. Min Act: -0.0001

Data Index: 457265 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1046686 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1174659 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4818. Min Act: -0.0001

Data Index: 102280 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4819. Min Act: -0.0000

Data Index: 962961 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4754. Min Act: -0.0000

Data Index: 49605 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4780. Min Act: -0.0001

Data Index: 1487374 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4605. Min Act: -0.0001

Data Index: 381629 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4618. Min Act: -0.0000

Data Index: 585847 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4578. Min Act: -0.0001

Data Index: 691788 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4887. Min Act: -0.0000

Data Index: 435769 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4715. Min Act: -0.0000

Data Index: 903265 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4676. Min Act: -0.0000

Data Index: 261999 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4527. Min Act: -0.0001

Data Index: 607664 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4490. Min Act: -0.0000

Data Index: 973462 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4510. Min Act: -0.0000

Data Index: 388674 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1721 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4521. Min Act: -0.0000

Data Index: 438898 (C4 (Web Text))

Max Activating Token Index: 323