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

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

Neuron 2457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.3090. Min Act: -0.0001

Data Index: 119770 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0706. Min Act: -0.0001

Data Index: 728631 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0612. Min Act: -0.0001

Data Index: 202613 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0865. Min Act: -0.0001

Data Index: 811578 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0407. Min Act: -0.0001

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0146. Min Act: -0.0001

Data Index: 63306 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0071. Min Act: -0.0001

Data Index: 821699 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9537. Min Act: -0.0001

Data Index: 631525 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9048. Min Act: -0.0001

Data Index: 812085 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9904. Min Act: -0.0001

Data Index: 733583 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9722. Min Act: -0.0001

Data Index: 747708 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9925. Min Act: -0.0001

Data Index: 838474 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9630. Min Act: -0.0001

Data Index: 1254334 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0043. Min Act: -0.0001

Data Index: 897180 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9682. Min Act: -0.0001

Data Index: 623450 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9663. Min Act: -0.0001

Data Index: 472839 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.8842. Min Act: -0.0001

Data Index: 638026 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9266. Min Act: -0.0001

Data Index: 796127 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.8995. Min Act: -0.0001

Data Index: 207431 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9248. Min Act: -0.0001

Data Index: 1357625 (C4 (Web Text))

Max Activating Token Index: 879