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

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

Neuron 3013 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.8072. Min Act: -0.0002

Data Index: 955569 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.8166. Min Act: -0.0002

Data Index: 575347 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.7150. Min Act: -0.0002

Data Index: 1095763 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.5682. Min Act: -0.0002

Data Index: 717579 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.5912. Min Act: -0.0002

Data Index: 314235 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.5486. Min Act: -0.0002

Data Index: 329363 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.5439. Min Act: -0.0002

Data Index: 1112700 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.5168. Min Act: -0.0002

Data Index: 266849 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.5412. Min Act: -0.0002

Data Index: 129954 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.5232. Min Act: -0.0002

Data Index: 1067827 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4727. Min Act: -0.0002

Data Index: 947408 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4983. Min Act: -0.0002

Data Index: 843638 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4667. Min Act: -0.0002

Data Index: 1007390 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4664. Min Act: -0.0002

Data Index: 959959 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4763. Min Act: -0.0002

Data Index: 885892 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4206. Min Act: -0.0002

Data Index: 811116 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4535. Min Act: -0.0002

Data Index: 423612 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4751. Min Act: -0.0002

Data Index: 131826 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4917. Min Act: -0.0002

Data Index: 574684 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.8166. Min Range: -1.8166

Max Act: 1.4662. Min Act: -0.0002

Data Index: 108150 (C4 (Web Text))

Max Activating Token Index: 78