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

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

Neuron 3640 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: 0.5919. Min Range: -0.5919

Max Act: 0.5899. Min Act: -0.0001

Data Index: 415737 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1147570 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5919. Min Act: -0.0000

Data Index: 401722 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5236. Min Act: -0.0000

Data Index: 818900 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1356620 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4775. Min Act: -0.0001

Data Index: 352387 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5117. Min Act: -0.0001

Data Index: 516788 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4876. Min Act: -0.0000

Data Index: 666636 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4495. Min Act: -0.0000

Data Index: 404539 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4642. Min Act: -0.0001

Data Index: 486043 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4779. Min Act: -0.0000

Data Index: 626077 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4928. Min Act: -0.0001

Data Index: 44047 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4884. Min Act: -0.0000

Data Index: 957323 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4506. Min Act: -0.0000

Data Index: 249924 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4619. Min Act: -0.0001

Data Index: 271656 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4342. Min Act: -0.0001

Data Index: 735505 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4776. Min Act: -0.0000

Data Index: 726845 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4548. Min Act: -0.0000

Data Index: 643680 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4544. Min Act: -0.0000

Data Index: 895970 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4681. Min Act: -0.0000

Data Index: 197854 (C4 (Web Text))

Max Activating Token Index: 467