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

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

Neuron 3710 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.8014. Min Act: -0.0001

Data Index: 721078 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.5287. Min Act: -0.0001

Data Index: 1273912 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2327. Min Act: -0.0001

Data Index: 945524 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.5045. Min Act: -0.0001

Data Index: 636900 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.4841. Min Act: -0.0001

Data Index: 979949 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.3860. Min Act: -0.0001

Data Index: 791433 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.3822. Min Act: -0.0001

Data Index: 1214512 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2977. Min Act: -0.0001

Data Index: 685513 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.3015. Min Act: -0.0001

Data Index: 608652 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2584. Min Act: -0.0001

Data Index: 957471 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2952. Min Act: -0.0001

Data Index: 601062 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.1945. Min Act: -0.0001

Data Index: 518444 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.1914. Min Act: -0.0001

Data Index: 808990 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2606. Min Act: -0.0001

Data Index: 28137 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2542. Min Act: -0.0001

Data Index: 966631 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2275. Min Act: -0.0001

Data Index: 678914 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.1948. Min Act: -0.0001

Data Index: 405346 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2978. Min Act: -0.0001

Data Index: 1219279 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.2447. Min Act: -0.0001

Data Index: 863831 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.8014. Min Range: -1.8014

Max Act: 1.1461. Min Act: -0.0001

Data Index: 1209729 (C4 (Web Text))

Max Activating Token Index: 654