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

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

Neuron 2007 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2913. Min Range: -4.2913

Max Act: 4.2913. Min Act: -0.0000

Data Index: 1165747 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 4.2913. Min Range: -4.2913

Max Act: 3.7378. Min Act: -0.0000

Data Index: 158069 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 4.2913. Min Range: -4.2913

Max Act: 3.5407. Min Act: -0.0000

Data Index: 1276278 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 4.2913. Min Range: -4.2913

Max Act: 3.1413. Min Act: -0.0000

Data Index: 676994 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 4.2913. Min Range: -4.2913

Max Act: 3.0348. Min Act: -0.0000

Data Index: 753363 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 4.2913. Min Range: -4.2913

Max Act: 3.0329. Min Act: -0.0000

Data Index: 290926 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.9829. Min Act: -0.0000

Data Index: 325679 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.8869. Min Act: -0.0000

Data Index: 399047 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.6364. Min Act: -0.0000

Data Index: 92434 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.6227. Min Act: -0.0000

Data Index: 178467 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.6272. Min Act: -0.0000

Data Index: 1289946 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.6016. Min Act: -0.0000

Data Index: 9198 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.5921. Min Act: -0.0000

Data Index: 1084839 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.5960. Min Act: -0.0000

Data Index: 1282306 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.5458. Min Act: -0.0000

Data Index: 646801 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.7773. Min Act: -0.0000

Data Index: 336693 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.4976. Min Act: -0.0000

Data Index: 406576 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.5014. Min Act: -0.0000

Data Index: 422568 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.4825. Min Act: -0.0000

Data Index: 341971 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 4.2913. Min Range: -4.2913

Max Act: 2.5583. Min Act: -0.0000

Data Index: 13740 (C4 (Web Text))

Max Activating Token Index: 795