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

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

Neuron 699 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3746. Min Act: -0.0001

Data Index: 338873 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3644. Min Act: -0.0001

Data Index: 727895 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3782. Min Act: -0.0001

Data Index: 1211987 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3513. Min Act: -0.0001

Data Index: 508 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3320. Min Act: -0.0001

Data Index: 955373 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3401. Min Act: -0.0001

Data Index: 845017 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3755. Min Act: -0.0001

Data Index: 333038 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3328. Min Act: -0.0001

Data Index: 220041 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3292. Min Act: -0.0001

Data Index: 105691 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3186. Min Act: -0.0001

Data Index: 603444 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3130. Min Act: -0.0001

Data Index: 444559 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3387. Min Act: -0.0001

Data Index: 603706 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3044. Min Act: -0.0001

Data Index: 614627 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3111. Min Act: -0.0001

Data Index: 237896 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3126. Min Act: -0.0001

Data Index: 652888 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3147. Min Act: -0.0001

Data Index: 950247 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.2993. Min Act: -0.0001

Data Index: 1344665 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1282264 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3499. Min Act: -0.0001

Data Index: 870947 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3074. Min Act: -0.0001

Data Index: 114235 (C4 (Web Text))

Max Activating Token Index: 267