Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2590 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0859. Min Act: -0.0004

Data Index: 919815 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0736. Min Act: -0.0004

Data Index: 433952 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0777. Min Act: -0.0004

Data Index: 775152 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0693. Min Act: -0.0004

Data Index: 535459 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0742. Min Act: -0.0004

Data Index: 372421 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0701. Min Act: -0.0004

Data Index: 577340 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0684. Min Act: -0.0004

Data Index: 404027 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0651. Min Act: -0.0004

Data Index: 478974 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0634. Min Act: -0.0004

Data Index: 556429 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0680. Min Act: -0.0004

Data Index: 391864 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0656. Min Act: -0.0004

Data Index: 956873 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0704. Min Act: -0.0004

Data Index: 1316153 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0618. Min Act: -0.0004

Data Index: 778118 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0644. Min Act: -0.0004

Data Index: 92630 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0641. Min Act: -0.0004

Data Index: 1042688 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0637. Min Act: -0.0004

Data Index: 453099 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0573. Min Act: -0.0004

Data Index: 1179802 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0641. Min Act: -0.0004

Data Index: 1359684 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0633. Min Act: -0.0004

Data Index: 1301127 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0605. Min Act: -0.0004

Data Index: 172443 (C4 (Web Text))

Max Activating Token Index: 12