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

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

Neuron 70 in Layer 0

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: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0001

Data Index: 969682 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0001

Data Index: 1107773 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0001

Data Index: 3176 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0001

Data Index: 103157 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0001

Data Index: 1022076 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0001

Data Index: 409456 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0001

Data Index: 1296856 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1246429 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0001

Data Index: 670788 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0052. Min Act: -0.0001

Data Index: 300250 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0001

Data Index: 47165 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0001

Data Index: 941482 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0052. Min Act: -0.0001

Data Index: 149407 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0052. Min Act: -0.0001

Data Index: 815675 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0051. Min Act: -0.0001

Data Index: 1159362 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0051. Min Act: -0.0001

Data Index: 279028 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0051. Min Act: -0.0001

Data Index: 497970 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0051. Min Act: -0.0001

Data Index: 1031205 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0051. Min Act: -0.0001

Data Index: 466561 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0050. Min Act: -0.0001

Data Index: 172222 (C4 (Web Text))

Max Activating Token Index: 521