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

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

Neuron 3830 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: 0.5568. Min Range: -0.5568

Max Act: 0.5568. Min Act: -0.0000

Data Index: 968224 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1176890 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1131154 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3287. Min Act: -0.0000

Data Index: 765464 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3379. Min Act: -0.0000

Data Index: 107198 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3366. Min Act: -0.0000

Data Index: 161218 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3349. Min Act: -0.0000

Data Index: 500961 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3103. Min Act: -0.0000

Data Index: 249324 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3039. Min Act: -0.0000

Data Index: 39933 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3151. Min Act: -0.0000

Data Index: 117403 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1223527 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.2920. Min Act: -0.0000

Data Index: 422945 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3159. Min Act: -0.0000

Data Index: 70997 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.2921. Min Act: -0.0000

Data Index: 171060 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1251579 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3105. Min Act: -0.0000

Data Index: 932986 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1334387 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.2786. Min Act: -0.0000

Data Index: 699890 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.2808. Min Act: -0.0000

Data Index: 789820 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.2790. Min Act: -0.0000

Data Index: 220296 (C4 (Web Text))

Max Activating Token Index: 609