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

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

Neuron 3840 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: 0.3702. Min Range: -0.3702

Max Act: 0.3702. Min Act: -0.0001

Data Index: 925561 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3426. Min Act: -0.0001

Data Index: 1139531 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3363. Min Act: -0.0001

Data Index: 703651 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3324. Min Act: -0.0001

Data Index: 273353 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3463. Min Act: -0.0001

Data Index: 630943 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3280. Min Act: -0.0001

Data Index: 161863 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3368. Min Act: -0.0001

Data Index: 730999 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3083. Min Act: -0.0001

Data Index: 247574 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2982. Min Act: -0.0001

Data Index: 227027 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3120. Min Act: -0.0001

Data Index: 556848 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3047. Min Act: -0.0001

Data Index: 1168904 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2968. Min Act: -0.0001

Data Index: 1173993 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2580. Min Act: -0.0001

Data Index: 441019 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2297. Min Act: -0.0001

Data Index: 128162 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2433. Min Act: -0.0001

Data Index: 308411 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.1909. Min Act: -0.0001

Data Index: 331351 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2271. Min Act: -0.0001

Data Index: 688104 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2097. Min Act: -0.0001

Data Index: 134435 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2390. Min Act: -0.0001

Data Index: 917270 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2153. Min Act: -0.0001

Data Index: 1065357 (C4 (Web Text))

Max Activating Token Index: 467