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

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

Neuron 3440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1137880 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.2565. Min Act: -0.0000

Data Index: 749583 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.2418. Min Act: -0.0000

Data Index: 104694 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.1876. Min Act: -0.0000

Data Index: 263316 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.1182. Min Act: -0.0000

Data Index: 581249 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0567. Min Act: -0.0000

Data Index: 184193 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1227685 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0683. Min Act: -0.0000

Data Index: 858646 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0651. Min Act: -0.0000

Data Index: 527296 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 1.2565. Min Range: -1.2565

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1157160 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0346. Min Act: -0.0000

Data Index: 146488 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.1047. Min Act: -0.0000

Data Index: 967143 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0261. Min Act: -0.0000

Data Index: 354024 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0045. Min Act: -0.0000

Data Index: 999781 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.2565. Min Range: -1.2565

Max Act: 0.9745. Min Act: -0.0000

Data Index: 539148 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 1.2565. Min Range: -1.2565

Max Act: 0.9194. Min Act: -0.0000

Data Index: 156165 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 1.2565. Min Range: -1.2565

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1173690 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0365. Min Act: -0.0000

Data Index: 338900 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 1.2565. Min Range: -1.2565

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1226883 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 1.2565. Min Range: -1.2565

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1080833 (C4 (Web Text))

Max Activating Token Index: 972