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

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

Neuron 2630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1042746 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1199002 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5874. Min Act: -0.0000

Data Index: 776412 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1243493 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5590. Min Act: -0.0001

Data Index: 110539 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5525. Min Act: -0.0000

Data Index: 673352 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5452. Min Act: -0.0000

Data Index: 955270 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5463. Min Act: -0.0000

Data Index: 637120 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5201. Min Act: -0.0000

Data Index: 505784 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4832. Min Act: -0.0000

Data Index: 997870 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5218. Min Act: -0.0000

Data Index: 571198 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4706. Min Act: -0.0000

Data Index: 130330 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1341626 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1007253 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5101. Min Act: -0.0000

Data Index: 152114 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1304863 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4547. Min Act: -0.0000

Data Index: 454177 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1313107 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4818. Min Act: -0.0000

Data Index: 857690 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4641. Min Act: -0.0000

Data Index: 84075 (C4 (Web Text))

Max Activating Token Index: 88