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

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

Neuron 254 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4890. Min Act: -0.0000

Data Index: 963344 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4683. Min Act: -0.0000

Data Index: 447920 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4317. Min Act: -0.0000

Data Index: 562032 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4648. Min Act: -0.0000

Data Index: 285457 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4638. Min Act: -0.0000

Data Index: 34664 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4106. Min Act: -0.0000

Data Index: 127025 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4251. Min Act: -0.0000

Data Index: 730133 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3940. Min Act: -0.0000

Data Index: 53225 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4037. Min Act: -0.0000

Data Index: 465750 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3806. Min Act: -0.0000

Data Index: 220439 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3873. Min Act: -0.0000

Data Index: 593090 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4034. Min Act: -0.0000

Data Index: 178499 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3779. Min Act: -0.0000

Data Index: 288962 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3724. Min Act: -0.0000

Data Index: 974580 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3499. Min Act: -0.0000

Data Index: 663301 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3445. Min Act: -0.0000

Data Index: 703281 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3615. Min Act: -0.0000

Data Index: 700116 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1041800 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3609. Min Act: -0.0000

Data Index: 410489 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3367. Min Act: -0.0000

Data Index: 896935 (C4 (Web Text))

Max Activating Token Index: 447