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

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

Neuron 2658 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5768. Min Act: -0.0003

Data Index: 366121 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5735. Min Act: -0.0002

Data Index: 552202 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5457. Min Act: -0.0003

Data Index: 577888 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5437. Min Act: -0.0002

Data Index: 426926 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5350. Min Act: -0.0003

Data Index: 869306 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5158. Min Act: -0.0003

Data Index: 1177569 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5137. Min Act: -0.0003

Data Index: 442507 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5313. Min Act: -0.0003

Data Index: 685516 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5305. Min Act: -0.0003

Data Index: 364232 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5448. Min Act: -0.0003

Data Index: 483813 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5205. Min Act: -0.0003

Data Index: 1129243 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5346. Min Act: -0.0003

Data Index: 398605 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5122. Min Act: -0.0003

Data Index: 630476 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5093. Min Act: -0.0003

Data Index: 877157 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4904. Min Act: -0.0003

Data Index: 438282 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5009. Min Act: -0.0003

Data Index: 571198 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4995. Min Act: -0.0003

Data Index: 1034293 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4992. Min Act: -0.0003

Data Index: 1350236 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4983. Min Act: -0.0003

Data Index: 1319673 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4958. Min Act: -0.0003

Data Index: 998686 (C4 (Web Text))

Max Activating Token Index: 411