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

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

Neuron 5081 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: 0.8808. Min Range: -0.8808

Max Act: 0.8163. Min Act: -0.0001

Data Index: 346249 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.8808. Min Act: -0.0001

Data Index: 783616 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7135. Min Act: -0.0001

Data Index: 664670 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7728. Min Act: -0.0001

Data Index: 740115 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6680. Min Act: -0.0001

Data Index: 29165 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6434. Min Act: -0.0001

Data Index: 427402 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6717. Min Act: -0.0001

Data Index: 1275211 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7224. Min Act: -0.0001

Data Index: 130730 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6995. Min Act: -0.0001

Data Index: 103903 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7017. Min Act: -0.0001

Data Index: 426136 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5967. Min Act: -0.0001

Data Index: 692428 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6141. Min Act: -0.0001

Data Index: 800578 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6739. Min Act: -0.0001

Data Index: 504037 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6948. Min Act: -0.0001

Data Index: 541932 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6469. Min Act: -0.0001

Data Index: 332009 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5771. Min Act: -0.0001

Data Index: 1133324 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6232. Min Act: -0.0001

Data Index: 925990 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6685. Min Act: -0.0001

Data Index: 284892 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7049. Min Act: -0.0001

Data Index: 989924 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6534. Min Act: -0.0001

Data Index: 994331 (C4 (Web Text))

Max Activating Token Index: 552