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

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

Neuron 6080 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8633. Min Act: -0.0002

Data Index: 1226913 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8578. Min Act: -0.0002

Data Index: 594454 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8345. Min Act: -0.0002

Data Index: 576415 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8001. Min Act: -0.0002

Data Index: 977606 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8087. Min Act: -0.0002

Data Index: 1195056 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8207. Min Act: -0.0002

Data Index: 697161 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8155. Min Act: -0.0002

Data Index: 670642 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8048. Min Act: -0.0002

Data Index: 596181 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7965. Min Act: -0.0002

Data Index: 898498 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7995. Min Act: -0.0002

Data Index: 746652 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7866. Min Act: -0.0002

Data Index: 1029235 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7806. Min Act: -0.0002

Data Index: 904934 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7759. Min Act: -0.0002

Data Index: 876695 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7861. Min Act: -0.0002

Data Index: 415703 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7737. Min Act: -0.0002

Data Index: 10881 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7737. Min Act: -0.0002

Data Index: 1254136 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7719. Min Act: -0.0002

Data Index: 724289 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7858. Min Act: -0.0002

Data Index: 1068570 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7773. Min Act: -0.0002

Data Index: 836320 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7795. Min Act: -0.0002

Data Index: 169242 (C4 (Web Text))

Max Activating Token Index: 757