Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2047 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.3069. Min Range: -4.3069

Max Act: 4.0217. Min Act: -0.0000

Data Index: 1062915 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 4.3069. Min Range: -4.3069

Max Act: 4.3069. Min Act: -0.0000

Data Index: 681383 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 4.3069. Min Range: -4.3069

Max Act: 4.0613. Min Act: -0.0000

Data Index: 389875 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.8487. Min Act: -0.0000

Data Index: 1241986 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.8202. Min Act: -0.0000

Data Index: 713221 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.9660. Min Act: -0.0000

Data Index: 330022 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.7940. Min Act: -0.0001

Data Index: 154507 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.9071. Min Act: -0.0001

Data Index: 922484 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.8719. Min Act: -0.0001

Data Index: 1237495 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.8680. Min Act: -0.0000

Data Index: 866901 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.8425. Min Act: -0.0000

Data Index: 625811 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.7025. Min Act: -0.0001

Data Index: 1186969 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.9629. Min Act: -0.0000

Data Index: 1049998 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.8122. Min Act: -0.0001

Data Index: 707225 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.9505. Min Act: -0.0001

Data Index: 225762 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.8076. Min Act: -0.0000

Data Index: 89376 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.9593. Min Act: -0.0001

Data Index: 1291918 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.7496. Min Act: -0.0000

Data Index: 78172 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.7497. Min Act: -0.0000

Data Index: 8159 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 4.3069. Min Range: -4.3069

Max Act: 3.7424. Min Act: -0.0000

Data Index: 302221 (C4 (Web Text))

Max Activating Token Index: 622