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

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

Neuron 1516 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6397. Min Act: -0.0002

Data Index: 465805 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5881. Min Act: -0.0001

Data Index: 626384 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5151. Min Act: -0.0001

Data Index: 154946 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5988. Min Act: -0.0001

Data Index: 1136121 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6739. Min Act: -0.0001

Data Index: 367240 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4471. Min Act: -0.0002

Data Index: 846394 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5663. Min Act: -0.0001

Data Index: 1275685 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5659. Min Act: -0.0002

Data Index: 640631 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5861. Min Act: -0.0001

Data Index: 112636 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5233. Min Act: -0.0001

Data Index: 869932 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5624. Min Act: -0.0001

Data Index: 673676 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5770. Min Act: -0.0001

Data Index: 997172 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4553. Min Act: -0.0002

Data Index: 710169 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4757. Min Act: -0.0001

Data Index: 145141 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5738. Min Act: -0.0001

Data Index: 797867 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5576. Min Act: -0.0001

Data Index: 858022 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4971. Min Act: -0.0002

Data Index: 728307 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5325. Min Act: -0.0001

Data Index: 1338847 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5535. Min Act: -0.0001

Data Index: 792590 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5483. Min Act: -0.0001

Data Index: 269242 (C4 (Web Text))

Max Activating Token Index: 717