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

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

Neuron 5043 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0641. Min Range: -1.0641

Max Act: 1.0641. Min Act: -0.0001

Data Index: 1020851 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9879. Min Act: -0.0000

Data Index: 22692 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8957. Min Act: -0.0000

Data Index: 469815 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8908. Min Act: -0.0000

Data Index: 66344 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1061775 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8457. Min Act: -0.0000

Data Index: 869116 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8592. Min Act: -0.0000

Data Index: 2988 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.7995. Min Act: -0.0000

Data Index: 251685 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8207. Min Act: -0.0000

Data Index: 165619 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8169. Min Act: -0.0001

Data Index: 910898 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8017. Min Act: -0.0000

Data Index: 976642 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1021090 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.7863. Min Act: -0.0000

Data Index: 805019 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.7817. Min Act: -0.0000

Data Index: 387815 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1275075 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.7531. Min Act: -0.0000

Data Index: 108612 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8065. Min Act: -0.0000

Data Index: 323196 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.7779. Min Act: -0.0000

Data Index: 510535 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8314. Min Act: -0.0000

Data Index: 161006 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1037474 (C4 (Web Text))

Max Activating Token Index: 935