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

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

Neuron 4273 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3399. Min Act: 0.0000

Data Index: 33420 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2926. Min Act: -0.0000

Data Index: 711899 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3112. Min Act: -0.0000

Data Index: 661057 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1037444 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2711. Min Act: -0.0000

Data Index: 877316 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3108. Min Act: -0.0000

Data Index: 82262 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2971. Min Act: -0.0000

Data Index: 829309 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1330083 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3449. Min Act: -0.0000

Data Index: 932255 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2974. Min Act: -0.0000

Data Index: 71224 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2867. Min Act: -0.0000

Data Index: 716555 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2958. Min Act: -0.0000

Data Index: 317509 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2736. Min Act: -0.0000

Data Index: 791753 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2805. Min Act: 0.0000

Data Index: 797270 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2727. Min Act: 0.0000

Data Index: 213245 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2768. Min Act: -0.0000

Data Index: 980047 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2663. Min Act: -0.0000

Data Index: 636190 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2686. Min Act: -0.0000

Data Index: 962886 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2723. Min Act: -0.0000

Data Index: 701554 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2622. Min Act: -0.0000

Data Index: 306182 (C4 (Web Text))

Max Activating Token Index: 735