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

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

Neuron 2491 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8672. Min Act: 0.0006

Data Index: 1271448 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8491. Min Act: 0.0003

Data Index: 1214222 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.9604. Min Act: -0.0000

Data Index: 989399 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8266. Min Act: -0.0000

Data Index: 414205 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8464. Min Act: 0.0005

Data Index: 304220 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.7701. Min Act: -0.0000

Data Index: 1150177 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6975. Min Act: 0.0006

Data Index: 683683 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6525. Min Act: 0.0005

Data Index: 1228444 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.7342. Min Act: 0.0002

Data Index: 590449 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6323. Min Act: 0.0002

Data Index: 849772 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1007781 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.4896. Min Act: -0.0000

Data Index: 64173 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5616. Min Act: 0.0000

Data Index: 634288 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5410. Min Act: 0.0002

Data Index: 717335 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5208. Min Act: 0.0002

Data Index: 901129 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5032. Min Act: -0.0000

Data Index: 444568 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.4933. Min Act: 0.0005

Data Index: 173458 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5121. Min Act: 0.0004

Data Index: 969966 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5033. Min Act: -0.0000

Data Index: 1357060 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.4976. Min Act: 0.0001

Data Index: 332741 (C4 (Web Text))

Max Activating Token Index: 246