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

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

Neuron 2774 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: 3.2676. Min Range: -3.2676

Max Act: 3.2676. Min Act: -0.0001

Data Index: 1004200 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2241. Min Act: -0.0001

Data Index: 1292487 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.0897. Min Act: -0.0001

Data Index: 623843 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.9014. Min Act: -0.0000

Data Index: 604020 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.7480. Min Act: -0.0001

Data Index: 714936 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.7551. Min Act: -0.0000

Data Index: 126643 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.8495. Min Act: -0.0001

Data Index: 1132969 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.5401. Min Act: -0.0001

Data Index: 1188777 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.6374. Min Act: -0.0001

Data Index: 161526 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.8979. Min Act: -0.0001

Data Index: 1005112 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.4836. Min Act: -0.0001

Data Index: 22035 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.6162. Min Act: -0.0001

Data Index: 324042 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.6859. Min Act: -0.0000

Data Index: 260009 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.5291. Min Act: -0.0001

Data Index: 1280455 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.4167. Min Act: -0.0000

Data Index: 199460 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.3752. Min Act: -0.0001

Data Index: 298692 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.4949. Min Act: -0.0000

Data Index: 302552 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.4627. Min Act: -0.0000

Data Index: 950677 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.4144. Min Act: -0.0001

Data Index: 952578 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 3.2676. Min Range: -3.2676

Max Act: 2.4045. Min Act: -0.0001

Data Index: 385975 (C4 (Web Text))

Max Activating Token Index: 11