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

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

Neuron 5789 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5841. Min Act: -0.0000

Data Index: 136314 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5269. Min Act: 0.0001

Data Index: 45360 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5350. Min Act: 0.0001

Data Index: 994852 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4969. Min Act: 0.0000

Data Index: 346748 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5270. Min Act: -0.0000

Data Index: 863724 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5211. Min Act: 0.0001

Data Index: 382697 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4863. Min Act: -0.0000

Data Index: 919532 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1280346 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5175. Min Act: 0.0000

Data Index: 35891 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4774. Min Act: 0.0001

Data Index: 983567 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4734. Min Act: 0.0000

Data Index: 39908 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4849. Min Act: 0.0000

Data Index: 796585 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4839. Min Act: -0.0000

Data Index: 737706 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4661. Min Act: 0.0000

Data Index: 982220 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4789. Min Act: 0.0001

Data Index: 1159141 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4826. Min Act: -0.0000

Data Index: 965148 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4387. Min Act: 0.0001

Data Index: 468588 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4723. Min Act: 0.0001

Data Index: 546571 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4697. Min Act: 0.0001

Data Index: 199688 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4865. Min Act: 0.0000

Data Index: 10210 (C4 (Web Text))

Max Activating Token Index: 269