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

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

Neuron 1143 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.7165. Min Act: -0.0001

Data Index: 1298360 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6360. Min Act: -0.0001

Data Index: 1070551 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5841. Min Act: -0.0001

Data Index: 1587850 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6012. Min Act: -0.0001

Data Index: 818981 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6590. Min Act: -0.0001

Data Index: 1045825 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6029. Min Act: -0.0000

Data Index: 295825 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5901. Min Act: -0.0001

Data Index: 359100 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5668. Min Act: -0.0001

Data Index: 1363357 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1446015 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5386. Min Act: -0.0001

Data Index: 1107984 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6147. Min Act: -0.0001

Data Index: 1656730 (Python Code)

Max Activating Token Index: 849

Text #11

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1522499 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5130. Min Act: -0.0000

Data Index: 817423 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5038. Min Act: -0.0000

Data Index: 382375 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.4874. Min Act: -0.0001

Data Index: 971803 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5567. Min Act: -0.0000

Data Index: 540736 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5229. Min Act: -0.0000

Data Index: 839527 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5053. Min Act: -0.0001

Data Index: 534596 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1026896 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5674. Min Act: -0.0001

Data Index: 726464 (C4 (Web Text))

Max Activating Token Index: 825