Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2964 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1302379 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.4132. Min Act: -0.0001

Data Index: 178209 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3949. Min Act: -0.0001

Data Index: 251913 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3806. Min Act: -0.0001

Data Index: 279364 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3513. Min Act: -0.0001

Data Index: 69391 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3340. Min Act: -0.0001

Data Index: 72256 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3424. Min Act: -0.0001

Data Index: 466126 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3526. Min Act: -0.0001

Data Index: 984952 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3374. Min Act: -0.0001

Data Index: 879795 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3165. Min Act: -0.0001

Data Index: 122189 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3353. Min Act: -0.0001

Data Index: 237970 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3124. Min Act: -0.0001

Data Index: 862406 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3000. Min Act: -0.0001

Data Index: 900192 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3211. Min Act: 0.0001

Data Index: 1224929 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3198. Min Act: -0.0001

Data Index: 124826 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1096527 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3063. Min Act: 0.0001

Data Index: 162649 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3239. Min Act: -0.0001

Data Index: 339405 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3023. Min Act: -0.0001

Data Index: 569814 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.4132. Min Range: -0.4132

Max Act: 0.3094. Min Act: -0.0001

Data Index: 218534 (C4 (Web Text))

Max Activating Token Index: 46