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

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

Neuron 2911 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8673. Min Act: -0.0000

Data Index: 73724 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6541. Min Act: -0.0000

Data Index: 278977 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5747. Min Act: -0.0001

Data Index: 272041 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5507. Min Act: -0.0000

Data Index: 232308 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5286. Min Act: -0.0001

Data Index: 918607 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5916. Min Act: -0.0000

Data Index: 1095558 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.3518. Min Act: -0.0000

Data Index: 1216525 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.4361. Min Act: -0.0001

Data Index: 227009 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.3676. Min Act: -0.0001

Data Index: 530147 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1075361 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.2798. Min Act: -0.0000

Data Index: 363026 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.3725. Min Act: -0.0001

Data Index: 419415 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.2747. Min Act: -0.0001

Data Index: 1132988 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.3095. Min Act: -0.0001

Data Index: 222151 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.1955. Min Act: -0.0000

Data Index: 710961 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.2403. Min Act: -0.0001

Data Index: 1009927 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1259336 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.2483. Min Act: -0.0001

Data Index: 29454 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.2806. Min Act: -0.0001

Data Index: 965012 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.2723. Min Act: -0.0001

Data Index: 1287638 (C4 (Web Text))

Max Activating Token Index: 766