Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 393 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6675. Min Act: -0.0003

Data Index: 1215783 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6529. Min Act: -0.0003

Data Index: 1210237 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6459. Min Act: -0.0003

Data Index: 466685 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6366. Min Act: -0.0003

Data Index: 484735 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6245. Min Act: -0.0003

Data Index: 546895 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6264. Min Act: -0.0003

Data Index: 104510 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6125. Min Act: -0.0003

Data Index: 661641 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5963. Min Act: -0.0003

Data Index: 854863 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5822. Min Act: -0.0003

Data Index: 505434 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5715. Min Act: -0.0003

Data Index: 800026 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6060. Min Act: -0.0003

Data Index: 802741 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5869. Min Act: -0.0003

Data Index: 1073692 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5607. Min Act: -0.0003

Data Index: 783274 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5653. Min Act: -0.0003

Data Index: 149044 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5779. Min Act: -0.0003

Data Index: 129838 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5970. Min Act: -0.0003

Data Index: 274921 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5970. Min Act: -0.0003

Data Index: 841364 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5848. Min Act: -0.0003

Data Index: 680789 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5778. Min Act: -0.0003

Data Index: 722944 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5942. Min Act: -0.0003

Data Index: 695 (C4 (Web Text))

Max Activating Token Index: 100