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

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

Neuron 1689 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4986. Min Act: -0.0002

Data Index: 235029 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4475. Min Act: -0.0002

Data Index: 647341 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4218. Min Act: -0.0002

Data Index: 1020523 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3815. Min Act: -0.0002

Data Index: 39303 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3820. Min Act: -0.0002

Data Index: 467089 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3689. Min Act: -0.0002

Data Index: 1167087 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3629. Min Act: -0.0002

Data Index: 277726 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3508. Min Act: -0.0002

Data Index: 865285 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3326. Min Act: -0.0002

Data Index: 944318 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3549. Min Act: -0.0002

Data Index: 312506 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3558. Min Act: -0.0002

Data Index: 477697 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3323. Min Act: -0.0002

Data Index: 746512 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3213. Min Act: -0.0002

Data Index: 45227 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3191. Min Act: -0.0002

Data Index: 499348 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3180. Min Act: -0.0002

Data Index: 397442 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3174. Min Act: -0.0002

Data Index: 1339365 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3144. Min Act: -0.0002

Data Index: 581866 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3014. Min Act: -0.0002

Data Index: 376449 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3147. Min Act: -0.0002

Data Index: 40412 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3044. Min Act: -0.0002

Data Index: 518019 (C4 (Web Text))

Max Activating Token Index: 77