Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4938 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.8437. Min Act: -0.0001

Data Index: 1047258 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.8162. Min Act: -0.0001

Data Index: 477142 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7551. Min Act: -0.0001

Data Index: 520785 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7152. Min Act: -0.0001

Data Index: 466743 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1204703 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6721. Min Act: -0.0001

Data Index: 716890 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6302. Min Act: -0.0001

Data Index: 542881 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1177478 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6897. Min Act: -0.0001

Data Index: 424034 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6850. Min Act: -0.0001

Data Index: 145092 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6198. Min Act: -0.0001

Data Index: 1292895 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5763. Min Act: -0.0001

Data Index: 612335 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6280. Min Act: -0.0001

Data Index: 857629 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5914. Min Act: -0.0001

Data Index: 345453 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6385. Min Act: -0.0001

Data Index: 1313579 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5493. Min Act: -0.0001

Data Index: 42139 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5648. Min Act: -0.0001

Data Index: 570439 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5799. Min Act: -0.0000

Data Index: 238367 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5518. Min Act: -0.0000

Data Index: 99528 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1126697 (C4 (Web Text))

Max Activating Token Index: 164