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

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

Neuron 3640 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.8161. Min Act: 0.0001

Data Index: 1223690 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.7807. Min Act: -0.0000

Data Index: 640892 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.7119. Min Act: -0.0000

Data Index: 623194 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6703. Min Act: 0.0000

Data Index: 1300598 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6782. Min Act: -0.0000

Data Index: 317202 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6821. Min Act: 0.0001

Data Index: 839582 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6756. Min Act: -0.0000

Data Index: 878456 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6549. Min Act: -0.0000

Data Index: 627672 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6454. Min Act: 0.0000

Data Index: 161384 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6581. Min Act: 0.0001

Data Index: 452590 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6417. Min Act: -0.0000

Data Index: 827054 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6176. Min Act: -0.0000

Data Index: 265348 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6134. Min Act: -0.0000

Data Index: 498027 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5890. Min Act: 0.0000

Data Index: 133450 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5796. Min Act: 0.0000

Data Index: 828710 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5718. Min Act: 0.0001

Data Index: 90082 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1107804 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1017742 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5819. Min Act: -0.0000

Data Index: 868157 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1008179 (C4 (Web Text))

Max Activating Token Index: 690