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

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

Neuron 165 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: 0.0938. Min Range: -0.0938

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1068712 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1138549 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1349046 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0818. Min Act: -0.0001

Data Index: 828051 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0001

Data Index: 664005 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1273276 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0803. Min Act: -0.0001

Data Index: 737876 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0779. Min Act: -0.0001

Data Index: 320423 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1072514 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1057417 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0862. Min Act: -0.0001

Data Index: 621244 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0765. Min Act: -0.0001

Data Index: 320465 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0756. Min Act: -0.0001

Data Index: 398959 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0839. Min Act: -0.0001

Data Index: 908202 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0706. Min Act: -0.0001

Data Index: 791657 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0629. Min Act: -0.0001

Data Index: 881734 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1289955 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1250917 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1044645 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0792. Min Act: -0.0001

Data Index: 499339 (C4 (Web Text))

Max Activating Token Index: 138