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

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

Neuron 3577 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5499. Min Range: -6.5499

Max Act: 6.5499. Min Act: -0.0000

Data Index: 534201 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 6.5499. Min Range: -6.5499

Max Act: 6.4959. Min Act: -0.0000

Data Index: 744759 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 6.5499. Min Range: -6.5499

Max Act: 6.1156. Min Act: -0.0000

Data Index: 678346 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.8853. Min Act: -0.0000

Data Index: 988724 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 6.5499. Min Range: -6.5499

Max Act: 6.2073. Min Act: -0.0000

Data Index: 546440 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.4465. Min Act: -0.0000

Data Index: 324258 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.9830. Min Act: -0.0000

Data Index: 436009 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.9152. Min Act: -0.0000

Data Index: 597613 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 6.5499. Min Range: -6.5499

Max Act: 6.0538. Min Act: -0.0000

Data Index: 783064 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 6.5499. Min Range: -6.5499

Max Act: 6.2231. Min Act: -0.0000

Data Index: 94031 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.9315. Min Act: -0.0000

Data Index: 685361 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.8946. Min Act: -0.0000

Data Index: 985216 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 6.5499. Min Range: -6.5499

Max Act: 6.0443. Min Act: -0.0000

Data Index: 749359 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.5852. Min Act: -0.0000

Data Index: 1197732 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.7779. Min Act: -0.0000

Data Index: 224834 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.9005. Min Act: -0.0000

Data Index: 460787 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.5164. Min Act: -0.0000

Data Index: 338819 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.6653. Min Act: -0.0000

Data Index: 42871 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.6284. Min Act: -0.0000

Data Index: 931314 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 6.5499. Min Range: -6.5499

Max Act: 5.6396. Min Act: -0.0000

Data Index: 996433 (C4 (Web Text))

Max Activating Token Index: 27