Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5885 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1199. Min Range: -2.1199

Max Act: 2.1199. Min Act: -0.0000

Data Index: 207118 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.5705. Min Act: -0.0000

Data Index: 449532 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.7229. Min Act: -0.0000

Data Index: 833318 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.6182. Min Act: -0.0000

Data Index: 777094 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.6112. Min Act: -0.0000

Data Index: 452403 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.5606. Min Act: -0.0000

Data Index: 460234 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.4752. Min Act: -0.0000

Data Index: 1227065 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.4551. Min Act: -0.0000

Data Index: 553257 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.5348. Min Act: -0.0000

Data Index: 258792 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.4261. Min Act: -0.0000

Data Index: 1591497 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.5147. Min Act: -0.0000

Data Index: 625398 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.4711. Min Act: -0.0000

Data Index: 1433301 (Python Code)

Max Activating Token Index: 683

Text #12

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1220213 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.3877. Min Act: -0.0000

Data Index: 432127 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.6144. Min Act: -0.0000

Data Index: 698342 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.3640. Min Act: -0.0000

Data Index: 298889 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1174689 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.4061. Min Act: -0.0000

Data Index: 46415 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1162238 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 2.1199. Min Range: -2.1199

Max Act: 1.4147. Min Act: -0.0000

Data Index: 363232 (C4 (Web Text))

Max Activating Token Index: 469