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

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

Neuron 3899 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3329. Min Range: -1.3329

Max Act: 1.3329. Min Act: -0.0000

Data Index: 1192663 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 1.3329. Min Range: -1.3329

Max Act: 1.0481. Min Act: -0.0000

Data Index: 995763 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.3329. Min Range: -1.3329

Max Act: 1.0387. Min Act: -0.0000

Data Index: 767608 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.3329. Min Range: -1.3329

Max Act: 1.0287. Min Act: -0.0000

Data Index: 463003 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.3329. Min Range: -1.3329

Max Act: 1.0021. Min Act: -0.0000

Data Index: 489796 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9922. Min Act: -0.0000

Data Index: 236175 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9510. Min Act: -0.0000

Data Index: 763436 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1205673 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1328567 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9675. Min Act: -0.0000

Data Index: 717888 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1162443 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9459. Min Act: -0.0000

Data Index: 153120 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9021. Min Act: -0.0000

Data Index: 193078 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8986. Min Act: -0.0000

Data Index: 228355 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9538. Min Act: -0.0000

Data Index: 431041 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9087. Min Act: -0.0000

Data Index: 97159 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1108807 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8444. Min Act: -0.0000

Data Index: 534113 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8521. Min Act: -0.0000

Data Index: 131802 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1310996 (C4 (Web Text))

Max Activating Token Index: 76