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

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

Neuron 2560 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: 1.0739. Min Range: -1.0739

Max Act: 1.0567. Min Act: -0.0000

Data Index: 957019 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1217371 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1353013 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0739. Min Act: -0.0000

Data Index: 609844 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9575. Min Act: -0.0000

Data Index: 92081 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8985. Min Act: -0.0001

Data Index: 12771 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8747. Min Act: -0.0000

Data Index: 87908 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8182. Min Act: -0.0000

Data Index: 523964 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9236. Min Act: -0.0000

Data Index: 906341 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8461. Min Act: -0.0000

Data Index: 532589 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7985. Min Act: -0.0000

Data Index: 906566 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8452. Min Act: -0.0000

Data Index: 844348 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8397. Min Act: -0.0000

Data Index: 308663 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8162. Min Act: -0.0000

Data Index: 694074 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8151. Min Act: -0.0000

Data Index: 193723 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7723. Min Act: -0.0000

Data Index: 795762 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1326314 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7785. Min Act: -0.0000

Data Index: 59685 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7495. Min Act: -0.0000

Data Index: 255696 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1000787 (C4 (Web Text))

Max Activating Token Index: 593