Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3571 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1630. Min Act: -0.0000

Data Index: 36040 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1391. Min Act: -0.0000

Data Index: 796572 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1298. Min Act: -0.0000

Data Index: 560613 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1284. Min Act: -0.0001

Data Index: 754605 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1255. Min Act: -0.0001

Data Index: 592829 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1319470 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1154. Min Act: -0.0000

Data Index: 969351 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1070. Min Act: -0.0001

Data Index: 313918 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1071. Min Act: -0.0000

Data Index: 26622 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1027. Min Act: -0.0001

Data Index: 294192 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1035. Min Act: -0.0000

Data Index: 280431 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1055. Min Act: -0.0000

Data Index: 563655 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.0976. Min Act: -0.0001

Data Index: 863552 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.0992. Min Act: -0.0000

Data Index: 30206 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.0874. Min Act: -0.0000

Data Index: 20431 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.0845. Min Act: -0.0001

Data Index: 649254 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.0813. Min Act: -0.0001

Data Index: 217445 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1629903 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1390766 (Python Code)

Max Activating Token Index: 81

Text #19

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.0811. Min Act: -0.0000

Data Index: 725103 (C4 (Web Text))

Max Activating Token Index: 290