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

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

Neuron 1035 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.7524. Min Act: -0.0001

Data Index: 706263 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6941. Min Act: -0.0001

Data Index: 673858 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6198. Min Act: -0.0001

Data Index: 1246731 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6820. Min Act: -0.0001

Data Index: 1185562 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5738. Min Act: -0.0001

Data Index: 994643 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5287. Min Act: -0.0001

Data Index: 1080545 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5848. Min Act: -0.0001

Data Index: 901625 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6052. Min Act: -0.0001

Data Index: 1287753 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5008. Min Act: -0.0001

Data Index: 157732 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5461. Min Act: -0.0001

Data Index: 641249 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4832. Min Act: -0.0001

Data Index: 187652 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5193. Min Act: -0.0001

Data Index: 520007 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5775. Min Act: -0.0001

Data Index: 38592 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5042. Min Act: -0.0001

Data Index: 508562 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4824. Min Act: -0.0001

Data Index: 162306 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5010. Min Act: -0.0001

Data Index: 361344 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4680. Min Act: -0.0001

Data Index: 812042 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4559. Min Act: -0.0001

Data Index: 1256759 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4447. Min Act: -0.0001

Data Index: 289673 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4973. Min Act: -0.0001

Data Index: 831756 (C4 (Web Text))

Max Activating Token Index: 718