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

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

Neuron 215 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: 0.4728. Min Range: -0.4728

Max Act: 0.4728. Min Act: -0.0001

Data Index: 586423 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.4015. Min Act: -0.0001

Data Index: 37942 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3972. Min Act: -0.0001

Data Index: 733546 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3724. Min Act: -0.0001

Data Index: 682688 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3755. Min Act: -0.0001

Data Index: 489902 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3631. Min Act: -0.0001

Data Index: 830418 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3684. Min Act: -0.0001

Data Index: 715834 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3839. Min Act: -0.0001

Data Index: 41913 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3542. Min Act: -0.0001

Data Index: 248680 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3340. Min Act: -0.0001

Data Index: 130606 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3331. Min Act: -0.0001

Data Index: 622785 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1127093 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3902. Min Act: -0.0001

Data Index: 251838 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3403. Min Act: -0.0001

Data Index: 754361 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3607. Min Act: -0.0001

Data Index: 641494 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3270. Min Act: -0.0001

Data Index: 109718 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3381. Min Act: -0.0001

Data Index: 895422 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3360. Min Act: -0.0001

Data Index: 887982 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.2950. Min Act: -0.0001

Data Index: 1346472 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.2796. Min Act: -0.0001

Data Index: 443310 (C4 (Web Text))

Max Activating Token Index: 680