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

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

Neuron 3886 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: 0.4941. Min Range: -0.4941

Max Act: 0.4941. Min Act: -0.0001

Data Index: 1157806 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4941. Min Act: -0.0001

Data Index: 279835 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4780. Min Act: -0.0001

Data Index: 320604 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4825. Min Act: -0.0002

Data Index: 213483 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4762. Min Act: -0.0001

Data Index: 447888 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4753. Min Act: -0.0001

Data Index: 718739 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4654. Min Act: -0.0001

Data Index: 1187998 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4692. Min Act: -0.0001

Data Index: 523502 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4670. Min Act: -0.0001

Data Index: 558208 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4725. Min Act: -0.0001

Data Index: 681571 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4673. Min Act: -0.0001

Data Index: 115094 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4621. Min Act: -0.0001

Data Index: 808203 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4569. Min Act: -0.0001

Data Index: 407750 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4627. Min Act: -0.0001

Data Index: 1075362 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4562. Min Act: -0.0001

Data Index: 180436 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4456. Min Act: -0.0001

Data Index: 1038262 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4427. Min Act: -0.0001

Data Index: 763173 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4557. Min Act: -0.0001

Data Index: 339706 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4408. Min Act: -0.0001

Data Index: 1333427 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4386. Min Act: -0.0001

Data Index: 484850 (C4 (Web Text))

Max Activating Token Index: 53