Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2308 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.6827. Min Act: -0.0000

Data Index: 1236864 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.9769. Min Act: -0.0000

Data Index: 1232216 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.7445. Min Act: -0.0000

Data Index: 190125 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.4683. Min Act: -0.0000

Data Index: 1135627 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.9865. Min Act: -0.0000

Data Index: 1071754 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.1124. Min Act: -0.0000

Data Index: 1129749 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.9401. Min Act: -0.0000

Data Index: 861627 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.2171. Min Act: -0.0000

Data Index: 1126802 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.7544. Min Act: -0.0000

Data Index: 864194 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.8572. Min Act: -0.0000

Data Index: 1075686 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.9719. Min Act: -0.0000

Data Index: 1050448 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.7091. Min Act: -0.0000

Data Index: 578392 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.6955. Min Act: -0.0000

Data Index: 1293934 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.7060. Min Act: -0.0000

Data Index: 1072310 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.5492. Min Act: -0.0000

Data Index: 501617 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.6676. Min Act: -0.0000

Data Index: 900356 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.4846. Min Act: -0.0000

Data Index: 306932 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.3630. Min Act: -0.0000

Data Index: 733387 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.5840. Min Act: -0.0000

Data Index: 1217957 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 3.9769. Min Range: -3.9769

Max Act: 2.5161. Min Act: -0.0000

Data Index: 320878 (C4 (Web Text))

Max Activating Token Index: 700