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

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

Neuron 2521 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1021. Min Act: -0.0001

Data Index: 662277 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1079868 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1079350 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0837. Min Act: -0.0001

Data Index: 106900 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0811. Min Act: -0.0001

Data Index: 415312 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0819. Min Act: -0.0001

Data Index: 257911 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0762. Min Act: -0.0001

Data Index: 708489 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0762. Min Act: -0.0001

Data Index: 468492 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0746. Min Act: -0.0001

Data Index: 589860 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0697. Min Act: -0.0001

Data Index: 72512 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1348235 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0734. Min Act: -0.0001

Data Index: 195586 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0683. Min Act: -0.0001

Data Index: 819782 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0646. Min Act: -0.0001

Data Index: 940016 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0652. Min Act: -0.0001

Data Index: 330574 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0654. Min Act: -0.0001

Data Index: 635245 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0693. Min Act: -0.0001

Data Index: 504869 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0682. Min Act: -0.0001

Data Index: 483171 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1119913 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1156769 (C4 (Web Text))

Max Activating Token Index: 492