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

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

Neuron 5873 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.2101. Min Act: -0.0000

Data Index: 8987 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0541. Min Act: -0.0000

Data Index: 816494 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1202785 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9386. Min Act: 0.0000

Data Index: 818989 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8311. Min Act: -0.0000

Data Index: 38622 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9104. Min Act: -0.0000

Data Index: 516706 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8441. Min Act: -0.0000

Data Index: 105139 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8869. Min Act: 0.0000

Data Index: 793124 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8299. Min Act: -0.0000

Data Index: 582944 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8513. Min Act: -0.0000

Data Index: 956008 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8694. Min Act: -0.0000

Data Index: 210503 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8561. Min Act: -0.0000

Data Index: 473775 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8042. Min Act: -0.0000

Data Index: 554947 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8457. Min Act: -0.0000

Data Index: 674555 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8396. Min Act: -0.0000

Data Index: 769037 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8404. Min Act: -0.0000

Data Index: 812879 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.7864. Min Act: -0.0000

Data Index: 370479 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8320. Min Act: -0.0000

Data Index: 919325 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8289. Min Act: -0.0000

Data Index: 49765 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8079. Min Act: -0.0000

Data Index: 942376 (C4 (Web Text))

Max Activating Token Index: 700