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

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

Neuron 1507 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.5066. Min Act: -0.0001

Data Index: 307038 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.4771. Min Act: -0.0001

Data Index: 12620 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1007785 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.3387. Min Act: -0.0001

Data Index: 223604 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.3314. Min Act: -0.0001

Data Index: 523023 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.3199. Min Act: -0.0000

Data Index: 998318 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2803. Min Act: -0.0000

Data Index: 31336 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.3042. Min Act: -0.0000

Data Index: 9876 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2929. Min Act: -0.0001

Data Index: 690116 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2666. Min Act: -0.0000

Data Index: 492911 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2806. Min Act: -0.0000

Data Index: 211782 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2722. Min Act: -0.0000

Data Index: 396777 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2612. Min Act: -0.0000

Data Index: 867609 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2555. Min Act: -0.0000

Data Index: 137632 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2557. Min Act: -0.0000

Data Index: 346049 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2561. Min Act: -0.0000

Data Index: 387225 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2637. Min Act: -0.0000

Data Index: 289879 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2514. Min Act: -0.0001

Data Index: 377087 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2490. Min Act: -0.0000

Data Index: 817630 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.5066. Min Range: -0.5066

Max Act: 0.2676. Min Act: -0.0001

Data Index: 230475 (C4 (Web Text))

Max Activating Token Index: 703