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

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

Neuron 5975 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: 2.7898. Min Range: -2.7898

Max Act: 2.7898. Min Act: -0.0000

Data Index: 434363 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 2.7898. Min Range: -2.7898

Max Act: 2.1774. Min Act: -0.0000

Data Index: 203989 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 2.7898. Min Range: -2.7898

Max Act: 2.1083. Min Act: -0.0000

Data Index: 1120766 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 2.7898. Min Range: -2.7898

Max Act: 2.0693. Min Act: -0.0000

Data Index: 619196 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.9935. Min Act: -0.0000

Data Index: 895731 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.7353. Min Act: -0.0000

Data Index: 230836 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 2.7898. Min Range: -2.7898

Max Act: 2.0462. Min Act: -0.0000

Data Index: 215679 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.7573. Min Act: -0.0000

Data Index: 641854 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.7541. Min Act: -0.0000

Data Index: 1001144 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.7917. Min Act: -0.0000

Data Index: 519692 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.7657. Min Act: -0.0000

Data Index: 1341294 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.6636. Min Act: -0.0000

Data Index: 209175 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.7173. Min Act: -0.0000

Data Index: 28565 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.7210. Min Act: -0.0000

Data Index: 908784 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.6968. Min Act: -0.0000

Data Index: 70688 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.7651. Min Act: -0.0000

Data Index: 1281769 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.6451. Min Act: -0.0000

Data Index: 254178 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.6019. Min Act: -0.0000

Data Index: 1343820 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.6044. Min Act: -0.0000

Data Index: 43561 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 2.7898. Min Range: -2.7898

Max Act: 1.5962. Min Act: -0.0000

Data Index: 860158 (C4 (Web Text))

Max Activating Token Index: 722