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

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

Neuron 4495 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.4054. Min Act: -0.0000

Data Index: 837997 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3140. Min Act: -0.0000

Data Index: 612553 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1332257 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2851. Min Act: -0.0000

Data Index: 304146 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2886. Min Act: -0.0000

Data Index: 444470 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2948. Min Act: -0.0000

Data Index: 675493 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1214446 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2932. Min Act: -0.0000

Data Index: 583513 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2843. Min Act: -0.0000

Data Index: 540318 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1174735 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3095. Min Act: -0.0000

Data Index: 640453 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2768. Min Act: -0.0000

Data Index: 570073 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1194211 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1172381 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1349375 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1344903 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2494. Min Act: -0.0000

Data Index: 958464 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2477. Min Act: -0.0000

Data Index: 541341 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2533. Min Act: -0.0000

Data Index: 610669 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2463. Min Act: -0.0000

Data Index: 201845 (C4 (Web Text))

Max Activating Token Index: 806