Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2659 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0004

Data Index: 784735 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0138. Min Act: -0.0004

Data Index: 939109 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0142. Min Act: -0.0004

Data Index: 1094765 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1095833 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0114. Min Act: -0.0004

Data Index: 250620 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0103. Min Act: -0.0004

Data Index: 957849 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0099. Min Act: -0.0004

Data Index: 853620 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0088. Min Act: -0.0004

Data Index: 16658 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1149646 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0105. Min Act: -0.0004

Data Index: 374120 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0077. Min Act: -0.0004

Data Index: 10927 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0096. Min Act: -0.0004

Data Index: 299524 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0089. Min Act: -0.0004

Data Index: 69638 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0086. Min Act: -0.0004

Data Index: 514135 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0087. Min Act: -0.0004

Data Index: 520402 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0095. Min Act: -0.0004

Data Index: 520874 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0085. Min Act: -0.0004

Data Index: 759219 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0084. Min Act: -0.0004

Data Index: 1198509 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0092. Min Act: -0.0004

Data Index: 165520 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0081. Min Act: -0.0004

Data Index: 1051498 (C4 (Web Text))

Max Activating Token Index: 695