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

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

Neuron 2756 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3486. Min Act: -0.0001

Data Index: 970077 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3579. Min Act: -0.0001

Data Index: 211379 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3002. Min Act: -0.0001

Data Index: 698313 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3818. Min Act: -0.0001

Data Index: 1047270 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2722. Min Act: -0.0001

Data Index: 1274346 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1260767 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2826. Min Act: -0.0001

Data Index: 453337 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2650. Min Act: -0.0001

Data Index: 810871 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2714. Min Act: -0.0001

Data Index: 687219 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2455. Min Act: -0.0001

Data Index: 538350 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2511. Min Act: -0.0001

Data Index: 987307 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2692. Min Act: -0.0001

Data Index: 525467 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2779. Min Act: -0.0001

Data Index: 107884 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2598. Min Act: -0.0001

Data Index: 1122654 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2681. Min Act: -0.0001

Data Index: 592614 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2639. Min Act: -0.0001

Data Index: 467289 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2665. Min Act: -0.0001

Data Index: 1181041 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2486. Min Act: -0.0001

Data Index: 426556 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2462. Min Act: -0.0001

Data Index: 613662 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2305. Min Act: -0.0001

Data Index: 54943 (C4 (Web Text))

Max Activating Token Index: 965