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

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

Neuron 4824 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: 0.4794. Min Range: -0.4794

Max Act: 0.4794. Min Act: -0.0000

Data Index: 765347 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4636. Min Act: -0.0000

Data Index: 266277 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4578. Min Act: -0.0000

Data Index: 124981 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4150. Min Act: -0.0000

Data Index: 766441 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4240. Min Act: -0.0000

Data Index: 896334 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4179. Min Act: -0.0000

Data Index: 964291 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3952. Min Act: -0.0000

Data Index: 450315 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4006. Min Act: -0.0000

Data Index: 122316 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4093. Min Act: 0.0000

Data Index: 858902 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3810. Min Act: -0.0000

Data Index: 406941 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3788. Min Act: -0.0000

Data Index: 951965 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3653. Min Act: 0.0001

Data Index: 111171 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1279526 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3731. Min Act: -0.0000

Data Index: 786596 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3636. Min Act: -0.0000

Data Index: 760629 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3512. Min Act: -0.0000

Data Index: 468993 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3588. Min Act: -0.0000

Data Index: 237804 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1119830 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3539. Min Act: -0.0000

Data Index: 647289 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3523. Min Act: -0.0000

Data Index: 943282 (C4 (Web Text))

Max Activating Token Index: 23