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

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

Neuron 2973 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7906. Min Range: -1.7906

Max Act: 1.7906. Min Act: -0.0000

Data Index: 889114 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.7906. Min Range: -1.7906

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1237582 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.7906. Min Range: -1.7906

Max Act: 1.2009. Min Act: -0.0000

Data Index: 876091 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.7906. Min Range: -1.7906

Max Act: 1.0708. Min Act: -0.0000

Data Index: 187006 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.7906. Min Range: -1.7906

Max Act: 1.1279. Min Act: -0.0000

Data Index: 411635 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.7906. Min Range: -1.7906

Max Act: 1.1300. Min Act: -0.0000

Data Index: 971468 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.7906. Min Range: -1.7906

Max Act: 1.0529. Min Act: -0.0000

Data Index: 387995 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 1.7906. Min Range: -1.7906

Max Act: 1.0262. Min Act: -0.0000

Data Index: 900932 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9106. Min Act: -0.0000

Data Index: 513175 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9971. Min Act: -0.0000

Data Index: 272170 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9893. Min Act: -0.0000

Data Index: 277119 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1230584 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9734. Min Act: -0.0000

Data Index: 347819 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1068189 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9365. Min Act: -0.0000

Data Index: 449740 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9478. Min Act: -0.0000

Data Index: 336191 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.8465. Min Act: -0.0000

Data Index: 714910 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.8158. Min Act: -0.0000

Data Index: 64121 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1114824 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.7906. Min Range: -1.7906

Max Act: 0.9120. Min Act: -0.0000

Data Index: 184075 (C4 (Web Text))

Max Activating Token Index: 196