Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1521 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0001

Data Index: 925699 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0511. Min Act: -0.0002

Data Index: 566059 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1298445 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0470. Min Act: -0.0001

Data Index: 667658 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1128432 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0476. Min Act: -0.0001

Data Index: 373810 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1047185 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0456. Min Act: -0.0002

Data Index: 353632 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0460. Min Act: -0.0001

Data Index: 546843 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0443. Min Act: -0.0002

Data Index: 186196 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0455. Min Act: -0.0002

Data Index: 398448 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0409. Min Act: -0.0002

Data Index: 88772 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0435. Min Act: -0.0001

Data Index: 520978 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0434. Min Act: -0.0002

Data Index: 539039 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0448. Min Act: -0.0001

Data Index: 338064 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1227622 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0423. Min Act: -0.0002

Data Index: 440323 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0422. Min Act: -0.0002

Data Index: 480711 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0428. Min Act: -0.0001

Data Index: 457004 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0411. Min Act: -0.0001

Data Index: 969578 (C4 (Web Text))

Max Activating Token Index: 229