Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5497. Min Act: -0.0001

Data Index: 1045691 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4837. Min Act: -0.0001

Data Index: 698260 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5649. Min Act: -0.0001

Data Index: 902493 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5660. Min Act: -0.0001

Data Index: 872712 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5594. Min Act: -0.0001

Data Index: 280558 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5213. Min Act: -0.0001

Data Index: 663166 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5004. Min Act: -0.0001

Data Index: 1089748 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5175. Min Act: -0.0001

Data Index: 800826 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4666. Min Act: -0.0001

Data Index: 1018197 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5102. Min Act: -0.0001

Data Index: 1099809 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5215. Min Act: -0.0001

Data Index: 823227 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4605. Min Act: -0.0001

Data Index: 74663 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4721. Min Act: -0.0001

Data Index: 770596 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4767. Min Act: -0.0001

Data Index: 79669 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4684. Min Act: -0.0001

Data Index: 563111 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1079581 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1088648 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4585. Min Act: -0.0001

Data Index: 645551 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4448. Min Act: -0.0001

Data Index: 294341 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4584. Min Act: -0.0001

Data Index: 171433 (C4 (Web Text))

Max Activating Token Index: 153