Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4264 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5896. Min Range: -2.5896

Max Act: 2.3936. Min Act: -0.0000

Data Index: 1160788 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 2.5896. Min Range: -2.5896

Max Act: 2.5896. Min Act: -0.0000

Data Index: 423553 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 2.5896. Min Range: -2.5896

Max Act: 2.2651. Min Act: -0.0000

Data Index: 18948 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 2.5896. Min Range: -2.5896

Max Act: 2.1519. Min Act: -0.0000

Data Index: 828840 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 2.5896. Min Range: -2.5896

Max Act: 2.1207. Min Act: -0.0000

Data Index: 82523 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.8363. Min Act: -0.0000

Data Index: 905649 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1158811 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.7838. Min Act: -0.0000

Data Index: 182365 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.6308. Min Act: -0.0000

Data Index: 1141917 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.6667. Min Act: -0.0000

Data Index: 442855 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.7725. Min Act: -0.0000

Data Index: 220297 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.6542. Min Act: -0.0000

Data Index: 1297750 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.6124. Min Act: -0.0000

Data Index: 202039 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.7635. Min Act: -0.0000

Data Index: 265251 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.5165. Min Act: -0.0000

Data Index: 259482 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1189671 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.4641. Min Act: -0.0000

Data Index: 1150765 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1308749 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.4637. Min Act: -0.0000

Data Index: 242233 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 2.5896. Min Range: -2.5896

Max Act: 1.4310. Min Act: -0.0000

Data Index: 478090 (C4 (Web Text))

Max Activating Token Index: 253