Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 491 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.7347. Min Act: -0.0000

Data Index: 143935 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6541. Min Act: -0.0000

Data Index: 178357 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6610. Min Act: -0.0001

Data Index: 26122 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6129. Min Act: -0.0000

Data Index: 113544 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6122. Min Act: -0.0000

Data Index: 776135 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6091. Min Act: -0.0000

Data Index: 888243 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6017. Min Act: -0.0001

Data Index: 164485 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6056. Min Act: -0.0000

Data Index: 461039 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5658. Min Act: -0.0000

Data Index: 263021 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5820. Min Act: -0.0001

Data Index: 822528 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5841. Min Act: -0.0000

Data Index: 640666 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5828. Min Act: -0.0000

Data Index: 980514 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5630. Min Act: -0.0000

Data Index: 966177 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5707. Min Act: -0.0000

Data Index: 199382 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5512. Min Act: -0.0000

Data Index: 608472 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5702. Min Act: -0.0001

Data Index: 405316 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5375. Min Act: -0.0000

Data Index: 699120 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1014600 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5720. Min Act: -0.0001

Data Index: 273956 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5571. Min Act: -0.0000

Data Index: 511349 (C4 (Web Text))

Max Activating Token Index: 519