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

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

Neuron 3037 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.4135. Min Act: -0.0001

Data Index: 1532178 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.2789. Min Act: -0.0001

Data Index: 45968 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.1494. Min Act: -0.0001

Data Index: 1216422 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.1384. Min Act: -0.0001

Data Index: 1527146 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.0030. Min Act: -0.0001

Data Index: 1441158 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.1179. Min Act: -0.0001

Data Index: 938055 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.0670. Min Act: -0.0001

Data Index: 1650154 (Python Code)

Max Activating Token Index: 549

Text #7

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.0526. Min Act: -0.0001

Data Index: 375333 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.0258. Min Act: -0.0001

Data Index: 1377248 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.0571. Min Act: -0.0001

Data Index: 1469455 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 1.4135. Min Range: -1.4135

Max Act: 0.9797. Min Act: -0.0001

Data Index: 1325829 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 1.4135. Min Range: -1.4135

Max Act: 0.9211. Min Act: -0.0001

Data Index: 1403599 (Python Code)

Max Activating Token Index: 137

Text #12

Max Range: 1.4135. Min Range: -1.4135

Max Act: 0.9963. Min Act: -0.0001

Data Index: 957188 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.4135. Min Range: -1.4135

Max Act: 0.9664. Min Act: -0.0001

Data Index: 516335 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 1.4135. Min Range: -1.4135

Max Act: 0.9277. Min Act: -0.0001

Data Index: 1228603 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 1.4135. Min Range: -1.4135

Max Act: 0.9446. Min Act: -0.0001

Data Index: 1342007 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.0525. Min Act: -0.0001

Data Index: 477897 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 1.4135. Min Range: -1.4135

Max Act: 0.9948. Min Act: -0.0001

Data Index: 1218835 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.0214. Min Act: -0.0001

Data Index: 1389731 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 1.4135. Min Range: -1.4135

Max Act: 0.9716. Min Act: -0.0001

Data Index: 1534903 (Python Code)

Max Activating Token Index: 20