Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.3772. Min Range: -8.3772

Max Act: 8.3772. Min Act: -0.0000

Data Index: 647370 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 8.3772. Min Range: -8.3772

Max Act: 8.3425. Min Act: -0.0000

Data Index: 574034 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 8.3772. Min Range: -8.3772

Max Act: 8.0981. Min Act: -0.0000

Data Index: 724787 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 8.3772. Min Range: -8.3772

Max Act: 8.0599. Min Act: -0.0000

Data Index: 545442 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 8.3772. Min Range: -8.3772

Max Act: 8.2295. Min Act: -0.0000

Data Index: 271795 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 8.3772. Min Range: -8.3772

Max Act: 8.0897. Min Act: -0.0000

Data Index: 215959 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.7955. Min Act: -0.0000

Data Index: 1344088 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.8027. Min Act: -0.0000

Data Index: 7115 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.5752. Min Act: -0.0000

Data Index: 788972 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.9048. Min Act: -0.0000

Data Index: 934547 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.6875. Min Act: -0.0000

Data Index: 1066983 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.8723. Min Act: -0.0000

Data Index: 32358 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.6840. Min Act: -0.0000

Data Index: 407896 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.6731. Min Act: -0.0000

Data Index: 784892 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.7020. Min Act: -0.0000

Data Index: 1009169 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.6728. Min Act: -0.0000

Data Index: 492103 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.9864. Min Act: -0.0000

Data Index: 889907 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.6184. Min Act: -0.0000

Data Index: 669074 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 8.3772. Min Range: -8.3772

Max Act: 7.7392. Min Act: -0.0000

Data Index: 182064 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 8.3772. Min Range: -8.3772

Max Act: 8.0753. Min Act: -0.0000

Data Index: 899287 (C4 (Web Text))

Max Activating Token Index: 857