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

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

Neuron 2511 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1154659 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2965. Min Act: -0.0000

Data Index: 628021 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1108310 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2827. Min Act: -0.0000

Data Index: 207130 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1261346 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2956. Min Act: -0.0000

Data Index: 803899 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2855. Min Act: -0.0000

Data Index: 803469 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2923. Min Act: -0.0000

Data Index: 392774 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2712. Min Act: -0.0000

Data Index: 770127 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1294111 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1150690 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2797. Min Act: -0.0000

Data Index: 626612 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2699. Min Act: -0.0000

Data Index: 127130 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2590. Min Act: -0.0000

Data Index: 214360 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2634. Min Act: -0.0000

Data Index: 757997 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2686. Min Act: -0.0000

Data Index: 982966 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2675. Min Act: -0.0000

Data Index: 280382 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1078534 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2554. Min Act: -0.0000

Data Index: 739214 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2564. Min Act: -0.0000

Data Index: 139361 (C4 (Web Text))

Max Activating Token Index: 283