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

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

Neuron 479 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: 1.0869. Min Range: -1.0869

Max Act: 1.0869. Min Act: -0.0001

Data Index: 387972 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9595. Min Act: -0.0001

Data Index: 602278 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9312. Min Act: -0.0001

Data Index: 667210 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9062. Min Act: -0.0001

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8790. Min Act: -0.0001

Data Index: 550366 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9040. Min Act: -0.0001

Data Index: 1194233 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9735. Min Act: -0.0001

Data Index: 283395 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9408. Min Act: -0.0001

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8208. Min Act: -0.0001

Data Index: 328597 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8113. Min Act: -0.0001

Data Index: 1175439 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9076. Min Act: -0.0001

Data Index: 905426 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8966. Min Act: -0.0001

Data Index: 800211 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8972. Min Act: -0.0001

Data Index: 11698 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8154. Min Act: -0.0001

Data Index: 1136778 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8823. Min Act: -0.0001

Data Index: 29551 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8621. Min Act: -0.0001

Data Index: 974666 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7612. Min Act: -0.0001

Data Index: 534321 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7992. Min Act: -0.0001

Data Index: 863757 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8879. Min Act: -0.0001

Data Index: 1161727 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7588. Min Act: -0.0001

Data Index: 224656 (C4 (Web Text))

Max Activating Token Index: 858