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

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

Neuron 598 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5850. Min Act: -0.0001

Data Index: 713683 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5834. Min Act: -0.0001

Data Index: 824519 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5375. Min Act: -0.0001

Data Index: 824889 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.6487. Min Act: -0.0001

Data Index: 1217595 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1001744 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5565. Min Act: -0.0001

Data Index: 292088 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5262. Min Act: -0.0001

Data Index: 1160278 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5061. Min Act: -0.0001

Data Index: 362040 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4873. Min Act: -0.0001

Data Index: 612195 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5152. Min Act: -0.0000

Data Index: 134408 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5013. Min Act: -0.0001

Data Index: 1359109 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4980. Min Act: -0.0001

Data Index: 617207 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4838. Min Act: -0.0001

Data Index: 685681 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5175. Min Act: -0.0001

Data Index: 596983 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4914. Min Act: -0.0001

Data Index: 598350 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4666. Min Act: -0.0001

Data Index: 554256 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4823. Min Act: -0.0001

Data Index: 1171921 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4933. Min Act: -0.0001

Data Index: 795103 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4617. Min Act: -0.0001

Data Index: 435592 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4688. Min Act: -0.0001

Data Index: 505215 (C4 (Web Text))

Max Activating Token Index: 376