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

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

Neuron 4258 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1347848 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1330870 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1208896 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1332894 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4741. Min Act: -0.0000

Data Index: 100213 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4522. Min Act: -0.0000

Data Index: 629275 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1096145 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5071. Min Act: -0.0000

Data Index: 57462 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4778. Min Act: -0.0000

Data Index: 512850 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4629. Min Act: -0.0000

Data Index: 10904 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4382. Min Act: -0.0000

Data Index: 803769 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4701. Min Act: -0.0000

Data Index: 993937 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1354826 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4321. Min Act: -0.0000

Data Index: 927611 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1631300 (Python Code)

Max Activating Token Index: 617

Text #15

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1225061 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3788. Min Act: -0.0000

Data Index: 883863 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3682. Min Act: -0.0000

Data Index: 698077 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1292973 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3410. Min Act: -0.0000

Data Index: 962772 (C4 (Web Text))

Max Activating Token Index: 86